Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2508.11017v3 Announce Type: replace Abstract: Large language models (LLMs) struggle with cross-lingual knowledge transfer: they sometimes hallucinate when asked in one language about facts expressed in a different language during training. This work introduces a controlled setting to study the causes and training dynamics of this phenomenon by training small Transformer models from scratch on synthetic multilingual datasets. Depending on (1) the correlation between facts and the language they were learned in (informativeness), and (2) the ease of language identification (extractability), models either develop unified representations across languages or separate representations; only when representations are unified do facts transfer across languages. Based on these insights, we propose a unifying perspective which explains a range of prior observations concerning cross-lingual transfer in multilingual LLMs. Our work shows controlled settings can shed light on pre-training dynamic
arXiv:2505.14104v2 Announce Type: replace Abstract: Legal rules encompass not only codified statutes but also implicit adjudicatory principles derived from precedents that contain discretionary norms, social morality, and policy. While computational legal research has advanced in applying established rules to cases, inducing legal rules from judicial decisions remains understudied across jurisdictions. The advent of Large Language Models (LLMs) offers unprecedented potential to automate the extraction of such latent principles, yet progress is stymied by the absence of formal task definitions and benchmarks. To address this gap, we formalize Legal Rule Induction (LRI) as the task of deriving concise, generalizable doctrinal rules from analogous precedents, distilling their shared preconditions, normative behaviors, and legal consequences. We further propose a reproducible pipeline for LRI dataset construction and, instantiating it on Chinese law as a representative jurisdiction, introd
arXiv:2608.27454v1 Announce Type: cross Abstract: Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution compl
arXiv:2608.27449v1 Announce Type: cross Abstract: To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, task success does not guarantee high-quality supervision: successful trajectories may still contain ineffective, redundant, or risky steps. Directly using such trajectories for SFT can introduce noisy supervision and encourage models to imitate undesirable problem-solving behaviors. Therefore, we propose SWE-Prime, a multi-granularity, two-stage SFT data selection method that progressively filters training data at the trajectory and segment levels. Specifically, the first stage performs trajectory-level screening based on process quality, result quality, and data representativeness, selecting a high-quality and representative subset of successful trajectories. The second stage performs segment-level se
arXiv:2608.27442v1 Announce Type: cross Abstract: In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming. Although recent work explores large language models (LLMs) for automated code review, most approaches oversimplify code review into a single-round, static decision task, which fails to capture the multi-round interactive nature and the complex problem-solving processes inherent in realistic review scenarios. To bridge this gap, we introduce MCR-Bench, the first defect state-aware benchmark designed for realistic multi-round code review. MCR-Bench covers five commonly-used programming languages and consists of 2,269 real-world multi-round code review tasks, each of which is annotated with fine-grained defect information and cross-round state labels. Each task in MCR-Bench is equipped with fine-grained defect metadata (e.g., description, type,
arXiv:2608.27391v1 Announce Type: cross Abstract: LLMs are increasingly able to answer complex questions about enterprise-scale document collections. But evaluation is hard: companies don't want to share internal communications, and synthetic datasets have been overly simple. We present CorporateBench (CB), a human-validated multi-task Q&A benchmark whose scale approaches the conditions LLMs encounter in corporate communication networks, with evaluation corpora surpassing 230,000 documents. CB evaluates LLMs across two dimensions (information extraction and knowledge base querying) through four synthetically generated firms ranging from 12 to 10,000 employees. Each corpus is sampled from a temporally evolving knowledge base describing a consistent world, guaranteeing cross-document logical consistency even across hundreds of thousands of documents. We evaluate five LLMs on CB, revealing increasingly poor performance as input size approaches realistic scales. CB provides LLM developers
arXiv:2608.27339v1 Announce Type: cross Abstract: Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Estimating both from target rollouts across four domains, four open-weight targets, and a frontier API target yields three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash
arXiv:2608.27266v1 Announce Type: cross Abstract: Efficiently improving autonomous agents across diverse tasks is central to accelerating recursive self-improvement (RSI) in agentic AI, with prompt optimization emerging as a promising approach capable of delivering performance gains comparable to those achieved by fine-tuning model weights, while reducing computational costs in both optimization and serving. However, recent developments increasingly favor unnecessarily complex prompt optimizers. We introduce Naive Prompt Optimization (NPO), a lightweight single-lineage method that iteratively revises prompts using a teacher model with rollout feedback. NPO achieves comparable or better performance than GEPA with fewer rollouts, and its advantage increases with stronger teacher models, suggesting that stronger teacher reasoning can partially substitute for optimizer-side search complexity. In interactive games, NPO remains broadly competitive with GEPA, while GRPO performs better on som
arXiv:2608.27260v1 Announce Type: cross Abstract: LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signals while producing experience that is useful rather than merely abundant. Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and conflate candidate construction with verification and selection. This work develops a two-level framework for the field. First, we represent agentic data as a common factorized object $(E,q,\tau,v)$, comprising an environment specification, task signal, interaction realization, and optional verifier. We organize generation paradigms by their primary anchor and dependency structure. Second, we formulate generation as constrained distribution design through the Accuracy-Complexity-divErsity (ACE) lens. A
arXiv:2608.27167v1 Announce Type: cross Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked the bare question: across 12 frontier models, commitment rises from 6.5% to 54.0% as evidence is escalated. It commits just as readily when every number on the panel is invented: fabricating the entire display, so nothing the model can see is true except the question itself, still lifts commitment from 24.5% to 36.8%, statistically indistinguishable from the 37.6% produced by genuine market data. What unlocks confident action is not information but the authority of its packaging. The failure is narrow and locatable. Incapacity is not the answer: on matched answerable questions attached to the same panels, the same models answer essentially always, at near-perfect accuracy. Nor is it belief - stated probabilities barely move across the gradient that swings action by 48 points, and score w
arXiv:2608.27070v1 Announce Type: cross Abstract: To mitigate catastrophic forgetting in downstream continual learning (CL) for large language models (LLMs), existing methods typically constrain parameter updates or introduce task-specific adaptation modules. However, these methods often rely on explicit task boundaries during training, limiting their applicability to realistic task-free scenarios. In this paper, we propose a \textbf{Fi}sher-guided \textbf{uni}fied (\textbf{FiUni}) framework for batch-level task detection and parameter-efficient continual adaptation. FiUni is motivated by a key observation about the Fisher information matrix (FIM) of pre-trained models: the orthogonality among the principal subspaces of its Kronecker-Factored Approximate Curvature (K-FAC) approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks. Based on this observation, FiUni constructs FIM-derived frozen subspaces to guide low-rank a
arXiv:2608.26978v1 Announce Type: cross Abstract: Landscapes are named, but whether names retain measurable environmental information beyond broad geographic structure is rarely tested. We analysed 3,757 Welsh settlements using a frozen, source-audited 24-element lexical framework, preregistered outcome-specific models and geographically structured validation. The central comparison contrasted 101 settlements carrying high-terrain elements (\textit{bryn} or \textit{mynydd}) with 139 carrying low-terrain elements (\textit{cwm} or \textit{pant}). High-terrain names occupied locations 24.4 m higher relative to their 2-km surroundings (95\% CI, 10.8--38.1 m; Holm-adjusted $p$ = 0.00137). The association remained positive across prespecified 1-, 2- and 5-km neighbourhood definitions and was reproduced using an independently produced elevation source (24.1 m; 95\% CI, 10.6--37.6 m). Adding terrain-name polarity to a non-lexical spatial and settlement baseline reduced geographically held-out
arXiv:2608.26970v1 Announce Type: cross Abstract: Place names provide persistent records of how landscapes have been described and organised, but their quantitative reuse requires explicit separation between mapped places, lexical annotations and environmental measurements. TEMPLAR Wales is a georeferenced environmental-toponymy dataset comprising 3,757 settlement records across Wales. The resource links a reproducible settlement frame to deterministic lexical screening and settlement-level environmental attributes through stable identifiers. It contains 1,350 lexical detections across 1,294 settlements, generated from a frozen registry of 24 Welsh place-name elements, while retaining exact- and prefix-token matches and their provenance separately. Environmental attributes describe river and coastal proximity, elevation and local terrain context at multiple spatial scales, land cover and neighbourhood woody cover, with parallel terrain measurements derived from independent elevation pr
arXiv:2608.26958v1 Announce Type: cross Abstract: Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and never mention the trait. In a controlled setup inspired by subliminal learning, a teacher induced to express a target trait generates restricted off-task data, such as number-only completions. Students trained on different amounts of independent off-task data are evaluated in a separate domain, with matched no-trait controls isolating target-specific transfer. Our main finding is that larger independent datasets make the teacher's induced trait stand out more clearly in the student's later behavior. Other plausible traits may also strengthen with scale, but the target usually grows more. When the small-scale student already
arXiv:2608.26950v1 Announce Type: cross Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented evaluation provides limited diagnostic value for identifying process-level failures or rigorous logic, failing to guide the transformation of LLMs into robust agents. To bridge this gap, we present a process-level benchmark designed to evaluate the inherent agentic mathematical reasoning abilities of LLMs. Our framework aligns problem-solving agentic behaviors with a structured taxonomy of reusable mathematical atomic capabilities. We design a comprehensive suite of planning, action, and feedback tasks across both textual and multimodal contexts, supported by an automated pipeline that synthesizes high-quality trajectories and produces fine-grained annotations via controlled LLM rewriting. Experiments reveal that models w
arXiv:2608.26921v1 Announce Type: cross Abstract: We introduce AraMS-28k, the largest publicly released line-level dataset of genuine historical Arabic manuscripts, comprising 14 books, 3,043 pages, and 28,600 annotated text lines (27,971 main-text, 629 margin). Thirteen books are hand-copied manuscripts spanning three script traditions -- Naskh, Ruq'ah, and Maghrebi -- and one is a lithographed printed edition included to broaden format diversity. Each line is labelled as main-text or margin, and margin lines that have an unambiguous attachment point in the main text are further annotated with an insertion anchor, recovering the manuscript's true non-linear reading order at line-level granularity -- to our knowledge the first such annotation released for a historical Arabic manuscript corpus. Because reference transcriptions are fully vocalised while manuscript hands are typically undiacritised, we release both the raw diacritised transcription and a diacritic-normalised counterpart f
arXiv:2608.26870v1 Announce Type: cross Abstract: Weak signals are early, low-visibility indicators that precede significant changes before those changes become established. Existing detection methods, based on keyword frequency, topic modeling, or untyped graph topology, fail to capture the semantic and relational structure through which such signals manifest. In this paper, we propose C-Unseen, a self-interpretable framework for weak signal detection in Dynamic Temporal Knowledge Graphs (DTKGs). We define a weak signal as a rare, semantically coherent subgraph that proliferates across consecutive TKG snapshots. The framework operates through two modules: a Rare Subgraphs Extractor, in which an LLM identifies subgraphs whose content is in tension with the dominant snapshot narrative via chain-of-thought reasoning, and a Weak Signal Alerter, in which the persistence of these rare subgraphs is tracked across time steps to isolate true weak signals. Experimental results demonstrate that
arXiv:2608.26836v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in natural language understanding, yet they struggle with strict multi-step reasoning, frequently suffering from hallucinations and inconsistency. Existing solutions like Chain-of-Thought (CoT) lack rigorous verification mechanisms, while standard Retrieval-Augmented Generation (RAG) often misses the complex, structural dependencies inherent in logical tasks. To bridge this gap, we propose a Neuro-Symbolic architecture that integrates a Logical Knowledge Graph (LKG) with dynamic solver routing. Specifically, we introduce an ontology-based LKG that treats logical rules and constraints as first-class topological nodes, enabling explicit modeling of dependencies extracted from text. We further design a Logic Router to dynamically dispatch tasks to the optimal symbolic engine, which is supported by a topology-aware hybrid retrieval mechanism. Experimental results on logic
arXiv:2608.26788v1 Announce Type: cross Abstract: Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-latency action sequences in unfamiliar environments. At the same time, world-model controllers excel at fast observation-to-action control, but lack open-ended task guidance. In this work, we combine these strengths into a single system, Instruct-to-Act, where we train a world-model controller to act autonomously at high frequency when conditioned on sparse, higher-latency, and high-level text instructions generated by a VLM planner. To train controllers to be language-instructable, we relabel segments of controller policy rollouts with synthetic instructions and jointly optimize a behavior-cloning objective along with existing reward-maximizing and world-modeling objectives. We evaluate our proposed approach across seven emb
arXiv:2608.26685v1 Announce Type: cross Abstract: Identifying white space --- the unexplored but potentially valuable regions of a patent landscape --- is essential for strategic R&D planning, yet existing methods rely on manual patent mapping or apply single-view clustering without quantitative gap detection. We propose BLANC (Blank Landscape Analysis through NPMI Conditioning), a three-phase pipeline combining (1) multi-view neural topic modeling along three semantic dimensions (application/use, novelty, inventive step); (2) Normalized Pointwise Mutual Information (NPMI) to quantify cross-dimensional cluster association; and (3) conditional detection that flags combinations whose NPMI drops when the corpus is filtered by a user-specified keyword. The drop is captured by a new metric, $\Delta$NPMI, which identifies combinations "established globally, unexplored locally." Because white space has no ground truth, we evaluate BLANC on two public USPTO corpora --- machine learning/AI (5,4
arXiv:2608.26602v1 Announce Type: cross Abstract: Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements, and explicit relation graphs add ongoing maintenance burden. We propose an entity-only external interface with task-conditioned relation materialization during inference. A two-layer index separates global routing from local entity focus and is evaluated on DeepSeek-V4-Flash and SWE-bench Verified. The base, one-layer, and two-layer conditions achieve 92.1%, 94.2%, and 95.6% success, respectively, under zero pre-built entity-relation edges.
arXiv:2608.26582v1 Announce Type: cross Abstract: Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable progress has been made in verifiable domains, self-evolution in unverifiable domains remains substantially less explored. We propose Judge co-adaptation from Zero data (J-Zero), a unified Challenger--Solver--Judge co-evolution framework that supports self-improvement across both domains. The Challenger and Solver co-evolve through an adversarial interaction: the Challenger generates increasingly difficult tasks, while the Solver learns to produce higher-quality responses to them. In parallel, the Judge co-adapts using preference pairs whose ordering is known in advance from how each response was produced, i.e., the Solver's answer over the Challenger's, and its decomposed-and-recombined answer over its one-shot answer, rather than from the Judge's own scores. J
arXiv:2608.26580v1 Announce Type: cross Abstract: Diffusion multimodal large language models (dMLLMs) have recently emerged as a new decoding paradigm for multimodal generation. Starting from a fully masked sequence, dMLLMs progressively decode the sequence by unmasking a subset of the remaining masked positions at each step. Since the selected tokens serve as the prediction context for subsequent steps, deciding which tokens to decode is crucial to the quality of the final output. The most common strategy prioritizes tokens based on a certainty measure that tends to favor tokens frequently observed in the training data. Recent approaches instead order tokens according to their influence on subsequent predictions, but do not explicitly account for the input image. We propose the Visual Information-Guided Sampler (VIG-Sampler), which prioritizes tokens based on their attention to image tokens. We further impose a constraint that penalizes candidate tokens whose image-attention distribut
arXiv:2608.26546v1 Announce Type: cross Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically separate tasks by application or capability and evaluate agents in environments that are cleaner and more stable than those encountered in practice. We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale production agent platform. Each task preserves the relevant pre-solution interaction history, persistent configurations, and workspace state, and is then validated through human verification. The resulting benchmark comprises 200 tasks spanning 8 broad scenarios and 17 fine-grained capability categories, with most tasks requiring multiple capability coordination. We execute these tasks in isolated Docker containers injected with three forms of real-world environmental complexity: Insufficient, Unstable,
arXiv:2608.26506v1 Announce Type: cross Abstract: Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior work primarily attributes merging risks to unsafe constituent models, implicitly assuming that merging individually aligned models preserves safety. In contrast, we show that model merging reveals a previously overlooked jailbreak risk rooted in the pretrained foundation model, even when all constituent models are individually safety-aligned. Motivated by this observation, we study a new threat setting where an attacker constructs jailbreak prompts that generalize across merged models sharing the same pretrained backbone, without access to the exact merging coefficients or constituent checkpoints. To exploit this phenomenon, we propose \textbf{Basin-Aware Jailbreak (BAJ)}, which formulates jailbreak generation as a min--max optimization over the merging space to produce transferable adversar
arXiv:2608.26480v1 Announce Type: cross Abstract: Multi-agent large language model systems are widely reported to beat single-model baselines, but the evidence is mixed, and comparisons are usually confounded: pipelines change token budgets, tool calls, and prompts simultaneously, so an aggregate gain rarely reveals what actually helped. We investigate the effect of introducing the manager-worker scaffold over a shared filesystem workspace, with no training and no per-benchmark tuning, measured against the same model answering in a single pass. Across nine models -- five open-weight, spanning 9B to ~2.8T parameters, and four frontier closed models -- on the 100 latest hard LiveCodeBench problems, the scaffold's benefit is real but conditional: large and statistically significant for some (Qwen3.8-27B +23.4, GPT-5.6-Luna +10.6 and GPT-5.6-Terra +8.0, each over five paired passes; Kimi-K3 +30.4 and Minimax-M3 +11.0 over five paired passes with reasoning off, both at $p < 10^{-4}$, and +4
arXiv:2608.26462v1 Announce Type: cross Abstract: Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more capable, understanding finetuning better becomes increasingly important, particularly since unwanted behaviors may arise during finetuning. In this paper, we introduce Diff Mining, a simple yet effective framework for identifying what a finetuned model has learned by comparing its logits to those of its base model. Diff Mining effectively surfaces salient tokens that are amplified in the finetuned model, serving as a fingerprint of its training -- even on text unrelated to the finetuning domain. Unlike many existing model diffing methods which require model internals, Diff Mining only needs access to output logits and scales to large models. The framework consists of two modular stages: (i) extracting per-context logit d
arXiv:2608.26442v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have shown that increased inference-time reasoning can improve performance on complex tasks. However, many existing approaches rely on fixed or preallocated reasoning controls, such as fixed token budgets, pre-execution difficulty estimates, or activation-space interventions, and are often evaluated on standalone reasoning benchmarks rather than full agentic workflows. These assumptions may not hold in agentic AI systems, where reasoning requirements evolve dynamically through planning, tool use, memory retrieval, and agent-to-agent interactions. Consequently, reasoning can become either excessive or insufficient, resulting in unnecessary computation, increased latency, planning drift, excessive tool use, or incomplete solutions. We argue that a major challenge for next-generation agentic AI is not merely how much reasoning a language model should perform, but how it should allocate reason
arXiv:2608.26432v1 Announce Type: cross Abstract: Voice agents must call tools and hold multi-turn dialogue entirely through speech, yet the dominant paradigm trains them in text. Existing frameworks either cascade TTS and ASR around a proprietary voice API, where gradients cannot flow and per-call cost makes on-policy reinforcement learning prohibitive, or stay in text: they measure voice agents but cannot improve them. We present SpeechGym, an audio-native agentic environment in which two omni-modal models converse in native audio, with no external ASR or TTS and no API boundary, over the unmodified tasks, tools and success check of an established text agentic benchmark, so that the interaction modality is the only variable and the loop stays local and trainable end to end. Audio agentic capability does not follow from audio understanding. The failures speech introduces are perceptual rather than reasoning deficits: the agent picks the right tool and the right argument slot but fills
arXiv:2608.26423v1 Announce Type: cross Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embedding dimensionality is empirically selected via cross-validated performance rather than fixed a priori, (ii) locating a relatively small set of latent support vectors (~ 29% of total training examples) representing influential prompts for identifying tokens that alter the classifier's predicted labels, and (iii) utilizing such tokens and their associated attack magnitudes for constructing a diagnostic taxonomy. This diagnostic taxonomy provides an end-to-end guideline for flagging prompts that require different treatments: rely Safely on the classifier's decision; flag Heuristic Bias and Heuristic Ove
arXiv:2608.26379v1 Announce Type: cross Abstract: Retrieval evaluation for retrieval-augmented generation (RAG) is increasingly designed around whether retrieved passages contain evidence that can support generation, rather than topical relevance alone. We study whether this closer alignment with downstream evidence needs also makes retrieval evaluation more useful for the decisions built from it. Across five retrieval benchmarks and an end-to-end TREC RAG 2025 setting, we examine an answer-support signal in four roles: comparing retrievers, guiding retrieval training and system selection, predicting downstream answer quality, and filtering the evidence supplied to a generator. The signal changes retrieval rankings, but its downstream value is not uniform. It does not reliably improve retriever training; the benefit of using it for system selection depends on how the generator is instructed to use the retrieved evidence; and retrieval scores based on it do not robustly predict answer q
arXiv:2608.26189v1 Announce Type: cross Abstract: Tool-using agents fail two ways: choosing the wrong tool, or forming wrong arguments, and an early failure of either kind can silently corrupt everything downstream. We measure a correct-invocation rate that separates the two, under both a clean teacher-forced context and the model's own free-running context, on five open-weight models over contamination-free multi-step tasks (depths 1-8). By depth 6, roughly 70% of a model's own clean-context capability is lost to its own earlier mistakes (L6 = 0.686, 0.684). Our central finding concerns the measurement itself. Under exact-match scoring against a fixed gold trajectory, a propagation model's severity and recovery parameters are not merely hard to estimate - they are fixed by the scoring rule. Severity is forced to its boundary (0 of 869 poisoned steps correct); recovery is structurally unobservable (0 of 580 poisoned steps returned on-track, against an expected 0.0058 by chance). Both f
arXiv:2608.26176v1 Announce Type: cross Abstract: AI systems whose outputs inform real decisions, and increasingly consequential ones, require something that current documentation practice does not provide: a structured, inspectable representation of the knowledge they need to ground, contextualize, and reason about those decisions, ideally reviewed and signed off by a domain expert. Established documentation artefacts already capture important aspects of an AI system. Model cards describe how a system behaves, data cards describe what it was trained on, and system cards describe the risks of a deployed system. None of them addresses the layer between inputs and outputs, more precisely, the concepts a system holds, the relationships it models, and the patterns of reasoning it applies. For pattern-recognition tasks this gap is tolerable. For agentic AI, where systems act on their conclusions, it is the step that most often separates a promising proof of concept from an operational solut
arXiv:2608.26132v1 Announce Type: cross Abstract: Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, relationship-property encoding, and relationship type. A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relati
arXiv:2608.26127v1 Announce Type: cross Abstract: Accurate forecasting of realized volatility ($RV$) is crucial for risk management and derivatives pricing. Although the implied volatility ($IV$) surface offers rich informational content, prevailing methods that treat it as a static image fail to capture its inherent dynamics. To overcome this limitation, we propose the Finance-Aware Graph Spatio-Temporal Network (FA-GSTN), a novel architecture that reframes $RV$ forecasting as modeling the evolution of a structured financial object. FA-GSTN builds a spatio-temporal graph sequence from the $IV$ surface, where nodes correspond to grid points and edges encode adaptive spatial (intra-day) and explicit temporal (inter-day) dependencies. The model incorporates domain knowledge through finance-aware node features (e.g., option Greeks) and tackles high-frequency noise via a multi-scale temporal smoothing gate coupled with an adaptive robust loss function. Comprehensive evaluations on a large-
arXiv:2608.26114v1 Announce Type: cross Abstract: Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-based constraints. Although Large Language Models (LLMs) perform strongly on natural language tasks, they often produce numerically incorrect yet plausible answers when solving multi-step financial calculations. To address this limitation, we introduce CIFQA (Calculation-Intensive Financial Query Answering), a deterministic tool-grounded multi-agent LLM framework for financial question answering. CIFQA separates language understanding from numerical execution by assigning specialized agents to query interpretation, routing, parameter extraction, computation planning, and response generation, while deterministic Python-based tools perform financial calculations and rule application. We instantiate CIFQA for fixed deposit query answering and evaluate it on a curated benchmark of fixed deposit
arXiv:2608.27455v1 Announce Type: new Abstract: Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitation, we introduce CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize failure modes derived from weaker models and incorporate them into inference through critique-based in-context examples. We propose two variants: CritICL-dynamic, which adaptively predicts input-specific failure modes and retrieves critiques, and CritICL-static, which uses a global failure mode profile to provide stable guidance. Experimental results s
arXiv:2608.27448v1 Announce Type: new Abstract: Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct. Building on this observation, we propose Test-Time Policy Optimization (TTPO), an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL. Token-level selection further refines both branches: distillation down-weights already-converged positions, while RL penalizes only confident errors. Bo
arXiv:2608.27428v1 Announce Type: new Abstract: Transduced language models (TLMs) compose a pretrained \emph{source} language model with a functional finite-state transducer to induce a language model over \emph{target} strings. Computing the probability of a target prefix under a TLM amounts to summing the source-model probabilities of all source strings that the transducer maps to target strings beginning with that prefix. This set can be exponentially large or infinite. Prior work uses a computational shortcut based on source prefix probabilities, then approximates the resulting sum with threshold-pruned beam summing. This produces a lower bound with unknown error. Instead, we resample source prefixes without replacement and reweight each selected prefix by the inverse of its inclusion probability. We show that applying this correction recursively gives an unbiased estimator of the target prefix probability and lets us estimate the mass lost by threshold pruning. Our beam-summing al
arXiv:2608.27420v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) significantly improves LLM reasoning but often causes a drop in policy entropy, leading to narrowed reasoning coverage and degraded pass@$k$ for large $k$. While existing methods mitigate this entropy collapse through algorithmic regularizations, cross-model non-parametric perturbation is also neglected. In this work, we propose a simple yet effective approach to preserve the generative diversity of LLMs during RLVR. Instead of relying solely on internal exploration, we force the target model to generate answers based on partial reasoning trajectories generated by a smaller, weaker language models. These unfamiliar prefixes effectively disrupt over-confidence and encourage the exploration of distinct reasoning paths. We empirically study the potential of outer prefixes, revealing the mechanism of the impact of distributional discrepancy to the exploration dynamics in RLVR training. Exp
arXiv:2608.27409v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves specific capabilities of large language models, but covering multiple capabilities often involves training separate domain experts and subsequently consolidating them. We organize three fusion paradigms by the artefacts they reuse: Merge combines expert task vectors, Mix RL pools their datasets, and multi-teacher on-policy distillation (MOPD) uses both. Because they have largely been studied in isolation, how they compare and how to choose among them remain unclear. We compare all three using shared experts and data across model scales and a multi-domain benchmark suite. Although their average performance differs by at most 1.4 points, the gap reaches 8.6 points on a single benchmark, with domain-level variation tracking cross-domain relations visible in task-vector geometry. Training dynamics expose distinct constraints: Mix RL depends on domain mixture proportions, MOPD rema
arXiv:2608.27402v1 Announce Type: new Abstract: How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organizing the relationships between them geometrically. We train six independent linear probes on open-weight language models, one per Moral Foundations Theory (MFT) category (care/harm, fair/cheat, lib/oppress, loy/betray, auth/subv, sanc/degrade), and examine how the resulting directions relate to each other in representation space. We find the directions neither collapse into a single moral detector nor isolate from one another. Rather, they span a near-maximal number of independent dimensions while sharing a positive common component. The shared component is the signature of integration, and it is moral-specific relative to a matched non-moral concept battery built identically (mean pairwise cosine 0.26 vs. 0.013). The geome
arXiv:2608.27397v1 Announce Type: new Abstract: Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerplate) that do not reflect patient state. We propose CAST (Concept-guided Artifact Suppression Tuning), an SAE-based framework for auditable clinical text classification. CAST uses Sparse Autoencoders to expose sparse, human-auditable features from intermediate Transformer activations, labels SAE latents with an LLM-assisted interpretation pipeline and ICD-10 retrieval constraints, suppresses verified artifact latents via residual subtraction during fine-tuning, and provides post-hoc per-concept attributions for auditing model decisions. On MIMIC-IV discharge-note mortality prediction, CAST improves over its corresponding fine-tuned encoder baselines and remains competitive with strong LLM baselines, while producing a feature-level audit trail of the clinical con
arXiv:2608.27394v1 Announce Type: new Abstract: Retrieved scientific literature can serve as inspiration for both human and AI scientists. Inspiration can take different forms: prior work may directly suggest how to address a problem, or surface directions at different levels of abstraction - zooming out to a more general view or zooming in to a concrete realization. We introduce RATIO (Retrieval Across Typed Ideation Operations), a large-scale benchmark in which relevance is defined by three operations which we name ideation moves: Address retrieves potential approaches for stated problems, Broaden retrieves more general formulations, and Specify retrieves concrete instantiations. RATIO is constructed from millions of full-text scientific papers across CS literature via a general recipe that extends discourse-marker distant supervision - previously used only for classification - to corpus-scale retrieval, combined with extensive LLM and human vetting. Experiments show that operation-s
arXiv:2608.27380v1 Announce Type: new Abstract: AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This framing breaks down for mixed-origin writing, where content origin and expression origin may differ. We cast mixed-origin detection as dimension-to-composition source attribution, inferring content origin and expression origin before composing them into four collaboration types. We propose Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label. On MixD2C, a reconstructed split derived from the HART mixed-origin benchmark, our disclosed D2C-Routing-based detector system reaches 0.8603 four-way Avg TPR@1%FPR, 6.5 points above the same-split RACE-local rerun. Core ablations support the routing design, while error analysis shows that distinguishing AI-cont
arXiv:2608.27370v1 Announce Type: new Abstract: Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communities. Although strong open-source efforts already exist, including open-weight models and open-source training recipes, a cost-efficient, hardware-accessible, and open-source pretraining recipe has long been missing. Even at a small scale, training Llama-3.2-3B costs over \$1.5M, and reproducing SmolLM3-3B needs over \$700K. In this report, we present an open pretraining recipe designed to lower this barrier. Using this recipe, we train a collection of Puro-2B models from scratch on up to 1.4 trillion tokens with FP8 precision on consumer-grade RTX 5090 GPUs. The models in the collection differ in token budgets and selected recipe variants. Our best model is trained at a compute cost of less than \$6.9K and approaches Qwen2.5-1.5B performance under our evaluation protocol. This cost efficie
arXiv:2608.27360v1 Announce Type: new Abstract: Speaker anonymization suppresses speaker-identifying attributes from speech while preserving linguistic content and quality. We propose repurposing XTTSv2, a multilingual voice cloning model trained on 27k hours of speech, for speaker anonymization without retraining. Our key insight is that XTTSv2's voice cloning capabilities preserve prosodic structure independently of speaker identity, enabling voice conversion by conditioning on a pseudo-speaker. We introduce an iterative refinement strategy that balances privacy and utility by maximizing a harmonic mean of speaker dissimilarity and intelligibility. Evaluated on seven European languages across CommonVoice and Multilingual LibriSpeech, our system achieves near-optimal privacy (EER $\approx$ 0.49), competitive intelligibility, and substantially better speech quality than dedicated anonymization baselines, while requiring no language-specific training. We release the code here: https://g
arXiv:2608.27358v1 Announce Type: new Abstract: Influential public discourse shapes public beliefs and can also mislead, not only through what is stated, but also through how information is framed, omitted, contextualised, and communicated. Yet less research has focused on how such misleadingness arises and shapes the interpretations formed by readers. To address this gap, we introduce Reader-Centric Misleadingness Understanding (RCMN), a framework that operationalises misleadingness through five dimensions: misleading mechanism, likely reader interpretation, evidence-warranted interpretation, emotional arousal, and communicative intent. Based on this framework, we construct an evidence-grounded dataset of influential public discourse. Empirical findings show that misleadingness is diverse and extends well beyond fabrication, with unsupported inference, exaggeration, and omission among the prevalent mechanisms, and is frequently associated with heightened emotional arousal and distorti
arXiv:2608.27348v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning. However, post-hoc CoT labels are too coarse to show how intent changes during generation. We introduce INTENT-AS-A-TOOL, an approach that adds intent-targeted tools to give the model a dedicated channel for expressing commitment to a target behavior. The probability of calling an intent tool provides a judge-free, fine-grained signal of the model's tendency to pursue that behavior. Our results show that INTENT-AS-A-TOOL complements CoT monitoring, expands post-hoc CoT labels into dense trajectories, and identifies critical steps for online intervention. These findings suggest that action prefere
arXiv:2608.27343v1 Announce Type: new Abstract: This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-level evidence consolidation and not fragment retrieval alone. The study focuses on a candidate set centered on essays by eighteenth-century Scottish philosopher David Hume, spanning books from ECCO (Eighteenth Century Collections Online) and historical newspapers. Because the input consists of fragmented reuse hits instead of clean document pairs, and positive coverage is inherently incomplete, we formulate the task as pair-level evidence consolidation into plausible transmission relations and compare three methodological families: a staged rule-based workflow, baselines (a decision tree and two direct LLM settings), and automated rule adaptation. On labeled ECCO--ECCO slices, pair-level feature aggregation alone already reaches 0.948 F1 on the main labeled slice, while the final workflow