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:2608.13831v1 Announce Type: cross Abstract: Spoken dialogue is a natural form of human--computer interaction, yet most speech language models remain limited to turn-based operation and lack real-time adaptability, such as user barge-in. Recent duplex speech-to-speech and speech-to-text models reduce latency by replacing multi-stage pipelines, but often compromise speech quality because accurate ASR, interruption handling, and high-fidelity synthesis must be optimized jointly. We propose VoiceChat-TTS, a low-latency, continuous, and streamable text-to-speech model for interactive agents. VoiceChat-TTS is driven directly by LLM text-token streams, supports explicit interruption via control tokens, and produces silence when no textual input is available. The model enables always-on, responsive speech generation while preserving modularity and high speech quality, and it supports mid-utterance interruptions without resetting the KV cache.
arXiv:2608.13787v1 Announce Type: cross Abstract: AI agents increasingly act on their users' behalf, handling tasks such as scheduling meetings, comparing offers, and haggling over prices. These principal-driven tasks routinely place the agent across from a counterpart (another user's agent, a seller, a recruiter) whose goals may conflict with its principal's. Yet the dispositions that make an assistant pleasant can make it a poor delegate: a friendly, helpful frontier model may disclose its principal's private information unprompted and concede at the first sign of resistance. We present SocialRL, a general recipe that trains social reasoning directly, and apply it to a 4B model across six domains: Deal-or-No-Deal, CaSiNo, Craigslist, Job Interview, Calendar, and Marketplace. Every domain is trained in-domain under the same recipe, and every policy is evaluated on all six. We find that (1) in-domain training reaches the frontier: on held-out scenarios the 4B matches or exceeds the GPT
arXiv:2608.13786v1 Announce Type: cross Abstract: Large language model (LLM) chatbots are increasingly used to answer clinical questions with citations to relevant clinical studies. Prior research has largely focused on citation fabrication, leaving a gap in evaluating the quality of retrieved studies and the factors driving their selection. In this study, we evaluated three general-purpose LLM chatbots: Claude Sonnet 5, Gemini 3.1 Pro, and ChatGPT GPT-5.5. We prompted the models with clinical questions adapted from 20 review questions in Issues 6 and 7 of the 2026 Cochrane Database of Systematic Reviews, simulating patient, clinician, and evidence-synthesis researcher roles. Each chatbot was queried under each user role with four independent repetitions, yielding 720 responses. Each chatbot was asked to support its answers with primary clinical citations, which we benchmarked against the included and excluded study sets of the Cochrane reviews. On average, a chatbot response retrieved
arXiv:2608.13721v1 Announce Type: cross Abstract: In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution. Recent likelihood-based response selection methods suggest that responses closer to the student distribution provide more effective supervision, motivating the hypothesis that high-likelihood responses may generally be preferable for fine-tuning. In this paper, we revisit this intuition and show that the value of likelihood-based data selection depends critically on model capacity and training duration. Through controlled experiments on mathematical reasoning, using students ranging from 1.5B to 8B parameters and supervision generated by stronger teacher models, we observe a clear \emph{capacity-dependent} ``{\color{SMALLCOLOR}\textbf{Fast-Fit}} / {\color{LARGECOLOR}\textbf{Slow-Gain}}'' pattern. High-likelihood data provides faster and more stable early improvements, espec
arXiv:2608.13626v1 Announce Type: cross Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source reach its natural post-action activation and compose. We organize the tests as an evidence lattice and validate the geometric branch on a known affine S_5 carrier: all held-source folds pass one-step, composition, inverse, decoding, and commutativity gates. Structured curvature and held-domain conjugacy raise error monotonically, but only 23/30 strongest cells flip a closure gate, bounding rather than universalizing calibration. In post-trained Qwen/Qwen3-4B, frozen final-token h28 affine maps have mean held-entity error .519, versus .398 for within-test-domain cross-fit. Seven randomized entity splits and map geometry do not support a purely entity-specific account. Earlier h4/h16 layers fit one-step transitions better, but h4 conflict-state decoding is weak and lexical controls remain
arXiv:2608.13622v1 Announce Type: cross Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or confirm before acting. This flexibility breaks a core assumption behind group-based RL: rollouts compared within a group are no longer guaranteed to be behaviorally comparable. As a result, reward-model preferences over interaction style can distort relative advantages and steer optimization toward reward-preferred behaviors rather than context-appropriate ones. We formalize this as a \textit{reward fairness problem} and propose \textbf{ARC} (Advantage Regularization via Conditioning), a training recipe that restores fairer relative comparison through strategy-conditioned rollout grouping, together with hybrid rewards and entropy regularization. We study ARC in our proposed \inter, a novel paradigm for responsive, steerable, and execution-aware user-agent interaction that decouples user-vis
arXiv:2608.13607v1 Announce Type: cross Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But aggregate gains say little about individual samples: an update can still cause sample-level regression, where a response correct under the old model becomes incorrect under the new one. This paper studies how to predict such regressions from signals available at inference time. We compare single-model signals (confidence, logit margin, attention entropy) against cross-version signals (output KL divergence, likelihood drift, token-level KL, representation drift) under a unified added-value test that isolates each signal's gain over a confidence baseline. Across six benchmarks in three task families (multiple-choice question answering, or MCQ; math reasoning; code generation) and six model update pairs, we find that (1) signal effectiveness is task-dependent: confidence is strongest on MCQ and simpler math, while likelihood/KL signals give t
arXiv:2608.13606v1 Announce Type: cross Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically,
arXiv:2608.13591v1 Announce Type: cross Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference. We study a different possibility: stable miscalibration, where a confident wrong answer remains locally stable under small perturbations. We combine two diagnostics: a label-aware output-level audit score that ranks domains by confidence variation and overconfident mistakes under a forced-answer baseline, and an internal sensitivity probe that measures hidden-state movement. On a multi-domain binary factual audit set, this audit score tracks where abstention-aware self-critique reduces decision loss, although direct labeled baselines rank the same gain more strongly. Internally, self-critical prompting consistently reduces hidden-state sensitivity across layers in three open-weight models. This supports prompt-induced local stabilization rather than a purely output-level abstention pattern, but it does not imply calibration: audi
arXiv:2608.13567v1 Announce Type: cross Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains a
arXiv:2608.14465v1 Announce Type: new Abstract: A frozen language model on reasoning tasks has two coupled weaknesses: it under-uses evidence its own residual stream already encodes, and it fails to detect when the input is insufficient to answer, so it confabulates. This paper consolidates two research lines that address these on the same residual stream: a conditional steering probe writes the stream at mid-stack layers and recovers reasoning accuracy from a frozen backbone, and a zero-shot sufficiency direction reads the stream and abstains when information is insufficient. Deployed in one forward pass they interfere: the steering write shifts the state the direction reads, costing up to 8 AUROC points of cross-domain transfer on small models; a separate clean pass doubles inference cost. We keep the direction fixed and train a small network to reconstruct the pre-steering residual from the steered one -- mean-squared error on (steered, clean) pairs, no sufficiency labels -- and rea
arXiv:2608.14457v1 Announce Type: new Abstract: The majority of work on summarization evaluation focuses on general summary quality (e.g., ROUGE, BERTScore) or specific desired properties (e.g., readability, factuality). However, these metrics fail to measure the utility of a summary to an individual user. For example, a biomedical researcher learning about the latest vaccine research will have different informational needs from a family doctor. Query-focused summarization captures part of this need, but in practice, users rarely state everything relevant in a query: a single short query is likely inadequate to distinguish the needs of a researcher from those of a physician. By contrast, a reader's background or persona (their role and expertise) is comparatively stable across queries and recovers much of this missing context, which makes it a practical signal for assessing whether a summary satisfies that reader's needs. In this work, we assess how sensitive popular summarization metr
arXiv:2608.14377v1 Announce Type: new Abstract: Sports have witnessed growing global enthusiasm in recent years, serving as a vital force for physical health, cultural exchange, social connection, and economic growth. The rapid advancement of large models, particularly (multimodal) large language models (M)LLMs, has demonstrated transformative potential to reshape sports understanding, analysis, and interaction across diverse domains. This paper presents a comprehensive survey of large models in sports, including (i) an overview of tasks and applications across different participant groups; (ii) a detailed analysis of sports-related datasets and benchmarks; and (iii) a critical discussion of current challenges and future directions. Our goal is to establish a foundation for advancing research and practical development of large-model-driven sports intelligence. An open-source GitHub repository is maintained at: https://github.com/Road2Redemption/Awesome_Large_Models_In_Sports1.
arXiv:2608.14361v1 Announce Type: new Abstract: Intrinsic dimensionality (ID) is widely used to probe the representational complexity of language models, but it remains unclear whether ID differences reflect properties of language itself or artefacts of how the underlying dataset was constructed. In this paper, we focus specifically on how lexical diversity, the number of unique last-token items present in a dataset, affects ID estimates of that dataset. We find a scale-dependent transition between two regimes: at low lexical diversity, conditions with fewer unique final words produce higher ID, while at high lexical diversity, this ordering reverses, and conditions with more unique words produce higher ID. We derive an exact, parameter-free formula for the point at which this reversal occurs, which matches the observed transition point at every scale tested. On the one hand, our results highlight how care must be taken when interpreting the intrinsic dimensionality of a set of represe
arXiv:2608.14312v1 Announce Type: new Abstract: Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such as few-shot, Self-Instruct, and Evol-Instruct apply the same prompting policy to every seed, even when the current policy would benefit from a harder, easier, or simply different task. We present Envs-FORGE, a prompting policy that converts verifier rewards into per-seed environment-synthesis actions. Envs-FORGE estimates seed pass rates, scores six projection--direction actions around a target learning frontier, and solves a per-seed mixed-integer linear program (MILP) to choose the action that conditions generation. The selected action drives synchronized rewriting of the instruction, fixtures, oracle solution, tests, and Docker environment; only gold-verified bundles enter RL training. The indexed MILP form also supports optional soft skill coverage for portfolio planning. On Qwen 3.5 35
arXiv:2608.14277v1 Announce Type: new Abstract: On-policy distillation (OPD) offers a promising way to transfer reasoning capabilities from stronger teacher models, but applying it to long-context reasoning teachers and short-context students introduces practical challenges, including tokenizer mismatch, teacher-student distribution mismatch, response length explosion, and training instability. In this work, we study this setting by transferring proof-reasoning capabilities from the long-context reasoning model SU-01 to short-context student models. To handle tokenizer differences, we perform OPD in a shared text space and align only tokens that occupy identical text spans under the student and teacher tokenizers. To mitigate the problem of excessive generation length and frequent truncation, we introduce a student reference KL loss and mask the advantages of special termination tokens such as and <|im_end|>. This strategy constrains the student from drifting excessively from its initi
arXiv:2608.14229v1 Announce Type: new Abstract: Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform gradient pressure regardless of training-data frequency. We propose the AdaPop (Adaptive Popularity) method, which combines local token confidence with a per-fact popularity-dependent exponent derived from an external proxy (e.g., Wikidata sitelinks, LLM-as-Judge), and automates the forget-retain balance via a dual-ascent controller that adjusts the retain penalty each epoch. Across three model families and two benchmarks, AdaPop leaks ~5x less forgotten content than competing methods under paraphrased queries and ~1.6x less under adversarial reformulations. We support our analysis with internal metrics: under our method, forget-set hidden states move further from the pre-unlearning model's states than under other methods, while retain-set representations remain close.
arXiv:2608.14210v1 Announce Type: new Abstract: Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious consequences. To better understand this problem, we conduct a fine-grained analysis of hallucination behavior in eight legal RAG systems across two legal corpora, the GDPR (in English) and a national civil law (in French). Using claim-level and answer-level evaluation, we report on hallucination density and severity, analyze performance across question categories and user personas, and validate our findings on an independent set of 142 legal-expert-authored questions. Our results show that hallucinations remain pervasive, ranging from less than 10% of responses for the best-performing systems to nearly half in the worst case. We further find that false-premise questions, containing incorrect assumptions that must be rejected, produce high hallucination rates on the manually-drafted questions
arXiv:2608.14150v1 Announce Type: new Abstract: The second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge evaluates two tasks over complete, unsegmented multilingual conversations: speaker diarization and recognition (Task 1) and conversational speech understanding (Task 2). Neither task provides oracle utterance boundaries or speaker labels at evaluation, and Task 2 provides no question-answer training set. For Task 1, we fine-tune VibeVoice-ASR-7B with random leading-silence cropping, consistent timestamp correction, and an exponential moving average (EMA) training strategy. For Task 2, we construct synthetic question-answer pairs through multimodal candidate generation, silent-audio filtering, and distribution-matched augmentation, and fine-tune Qwen3-Omni-30B-A3B-Instruct for tagged direct answering. On the Task 1 evaluation set, cropping reduces tcpMER from 18.30% to 17.27%, and EMA further reduces it to 16.73%. On the Task 2 evaluation set, jointly applying
arXiv:2608.14079v1 Announce Type: new Abstract: Silicon sampling can produce surprisingly good population estimates at times. Does doing it fast attenuate such fidelity? In this study, we extend and assess ongoing work in silicon sampling by comparing the algorithmic fidelity of "fast" and "slow" modes of silicon sampling among a nationally representative sample of Singaporean survey respondents. We find that silicon sampling with contemporary frontier models remains a method in early development to be used only with great caution. While silicon samples are able to produce moderately faithful estimates of population means, they continue to understate opinion variance and distort the latent contextual space behind human opinions. Conditional on such limitations, we find "fast" modes of silicon sampling to be relatively superior to traditional "slow" modes of silicon sampling. Fast silicon sampling is significantly more efficient in compute resources and run-time while being monotonicall
arXiv:2608.14055v1 Announce Type: new Abstract: Authoritative scientific knowledge in geoscience remains largely trapped in legacy monographs and historical literature, where unstructured text and complex layouts hinder computational access. We introduce HERMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents. Using a coordinating large language model, HERMES integrates domain constraints, validation rules and evidence tracing within a unified document-level extraction process that incorporates parsed text, tables, figures and captions. Applied to the 55-volume Treatise on Invertebrate Paleontology, the system produced a structured database of 32,277 fossil taxonomic entities and 451,878 attributes, released online at https://treatise.geolex.org. Extraction performance remained stable across fossil groups (average F1 scores of approximately 0.90 for entities and 0.91 for attributes), improving per-volume efficiency approximately sixfo
arXiv:2608.14029v1 Announce Type: new Abstract: Multimodal dialogue retrieval aims to retrieve dialogues from multimodal dialogue banks that are similar to a target dialogue in terms of both textual semantics and acoustic conversational styles. Such dialogue-level retrieval is crucial for many dialogue-related tasks, including Emotion Recognition in Conversation, Spoken Dialogue Systems, and Conversational Speech Synthesis, where external dialogue examples can provide valuable semantic and stylistic references. However, existing retrieval methods are still largely limited to utterance-level or unimodal matching, and often fail to capture the global semantic coherence and stylistic consistency of an entire dialogue. To address this gap, we propose S2Dialog, a unified framework for dialogue-level semantic-style retrieval from multimodal dialogue banks. Specifically, S2Dialog consists of a Dialogue-level Textual Retriever and a Dialogue-level Acoustic Retriever, which encode the textual a
arXiv:2608.14003v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chain-of-thought generation, but incur substantial computational costs during inference. In production settings, batched inference is essential for high throughput, yet the existing training-free adaptive pruning methods we evaluate severely degrade in this regime. Because a batch must share a single pruning mask, these methods aggregate activations across samples and then apply threshold-based selection; the threshold, calibrated offline on unaggregated activations, no longer matches the aggregated distribution, so the realized sparsity ratio drifts and accuracy on reasoning tasks collapses under batched inference. In this work, we propose a training-free adaptive pruning method designed specifically for batched inference in LRMs, built on two components. First, we replace threshold-based selection with periodic top-k selection over the aggregated
arXiv:2608.13959v1 Announce Type: new Abstract: Function calling is what the recent accounting of constrained generation explicitly sets aside: it finds the decoder's contribution small for format constraints, then warns in its Section 7 against extrapolating where a constraint encodes a correctness requirement, and names function calling as one. Tool abstention is that case at its sharpest: an enum leaves the wording of an answer alone and narrows the set of answers there are, and declining to call anything is the first it drops. We measure the excluded case. Three conditions over one byte-identical prompt separate a grammar's two jobs: it fixes where generation stops as well as which tokens may be emitted. We evaluate open-weight models from 0.6B to 4B on matched English and Korean items, so the language comparison is made within item. Against an unconstrained decoder, prior work's contrast is negative on abstention in four of six cells with intervals excluding zero, worst -29.5 poin
arXiv:2608.13947v1 Announce Type: new Abstract: High-quality creative writing data for large language models (LLMs) remains dominated by story-centric data, limiting models' ability to follow the structural and functional conventions of diverse creative formats. We propose an attribute-guided genre expansion framework for scaling creative writing data beyond story generation. By separating thematic breadth from genre-form control, our framework leverages human-authored story prompts as diverse creative seeds, while utilizing manually curated genre attributes to enforce distinct structural, stylistic, and formatting conventions. We combine these to prompt strong LLMs for genre-faithful query-response pairs, which are then quality-filtered. Applying this framework, we construct the Multi-Genre Collection, a 50K-example corpus spanning 13 creative genres, including story, rap, lyrics, scripts, game design, character design, and other creative formats. Experiments across out-of-distributio
arXiv:2608.13854v1 Announce Type: new Abstract: Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular languages such as C++, Java, and Python. This leaves a niche, many-to-many setting where parallel supervision is sparse, producing plausible but non-executable translations. We address this setting with preference-based reinforcement learning driven by execution-based supervision. Our pipeline firstly expands verifiable seed Python programs into a multilingual pool of execution-validated codes. Using the pool, a base LLM generates translation candidates across language pairs, which we label by their execution outcomes. The resulting preferences are used to train a reward model that scores cross-language translation quality. Finally, we optimize our base LLMs with GRPO over 600 directed language pairs (25 x 24) using the reward model as a signal. To evaluate the niche translation capability,
arXiv:2608.13835v1 Announce Type: new Abstract: Dynamic topic models capture evolving word distributions, but traditional coherence metrics may fail when vocabulary changes while semantic meaning persists. We evaluate 120 topics from CoNTM and DLDA across NYT, DBLP, and arXiv, using three human annotators and Low, Medium, and High lexical-change categories. Traditional temporal coherence shows highly variable agreement with human judgments ($\rho$=-0.256 to 0.614). In contrast, LLM-based semantic similarity agrees strongly with human semantic judgments for CoNTM on NYT ($\rho$=0.609), DBLP ($\rho$=0.721), and arXiv ($\rho$=0.502), but is less consistent for DLDA. Lexical-change stratification reveals variation hidden by aggregate evaluation. We therefore advocate lexical-change-aware evaluation, jointly reporting traditional coherence and LLM-based semantic measures as complementary rather than interchangeable signals.
arXiv:2608.13760v1 Announce Type: new Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors? This distinction is important because reasoning-oriented training can make traces look more deliberative without amplifying the behaviors most tied to model correctness. We quantify this mismatch with Behavioral Lift, a metric that measures how much correctness changes when a behavior is present versus absent in a model's reasoning trace. Across 15 models and 6 benchmarks spanning text-only and vision-language reasoning, we annotate 15,282 traces with a taxonomy whose core behaviors are defined for both LLM and VLM traces. We find evidence for an Amplification-Lift Gap, in which thinking models strongly amplify self-correction, hypothesis testing, and uncertainty acknowledgment, while the highest-lift behaviors are confidence calibration, knowledge alignment, and self-awareness. Confidence calibr
arXiv:2608.13741v1 Announce Type: new Abstract: Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned generators either take caption embeddings frozen from off-the-shelf text encoders, or adapt the encoder end-to-end, letting the denoising loss shape the embeddings only as a by-product. In either case, the conditioning representation is never deliberately matched to the signal modality, leaving it ill-suited to guide generation. We address this by introducing GALA: Generation-Aware cross-modaL Alignment for text conditional time series generation. GALA is a two-stage approach that first contrastively couples a pretrained text encoder with a time-series foundation model into a shared embedding space with both encoders adapted to generation by an auxiliary generative loss, and then freezes the resulting caption embedding to drive a flow-matching generator. On TSFragment-600K, spann
arXiv:2608.13722v1 Announce Type: new Abstract: This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.
arXiv:2608.13717v1 Announce Type: new Abstract: Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We present StreamHear, a semi-supervised pipeline that adapts a pretrained streaming student by fine-tuning an offline transducer teacher on the labeled training set, generating pseudo-labels on the unlabeled portion, and fine-tuning the student on the mixture. We further introduce a prior-regularized dynamic-programming realignment step that fixes chunk-level word placement using an ASR-hypothesis anchor. Across four datasets spanning financial calls, prepared read speech, and phone-quality dialogue, StreamHear consistently outperforms supervised student fine-tuning and narrows the gap to the offline teacher.
arXiv:2608.13708v1 Announce Type: new Abstract: Automatically generating textbook-grounded assessment items can reduce science teachers' workload, but existing retrieval-augmented generation (RAG) systems rely on flat retrieval, support only single-question generation, lack safeguards against weak evidence, and are ill-suited to low-resource, board-exam-structured curricula. We address these limitations with TeachMateGPT, a multi-agent system contributing four advances to curriculum-grounded science-assessment authoring. (i) COPE, a hierarchical knowledge base replacing token-window chunking with a multi-resolution index that segments documents along syllabus structure and links them at three granularities via a traversable graph-based lineage, matching evidence to each topic's instructional level. (ii) A staged, fail-closed agent pipeline replacing one-shot retrieve-then-generate: routing gates search, retrieval fuses dense and lexical evidence under a coverage gate that withholds gen
arXiv:2608.13706v1 Announce Type: new Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text. To close this gap, we present CLAIR-Fin, a nine-agent framework that decomposes each question into atomic claims maintained in a typed Financial Claim Ledger. Each claim is resolved through Asymmetric Evidence Authority, which conditions evidence trust on claim type rather than treating all modalities as equally reliable; Chain-of-Custody Verification, which checks grounding at the hand-off between drafting and adversarial review rather than only at the pipeline's exit; an Adaptive Rebuttal Cycle, which routes contested claims through adversarial debate whose depth scales with what that debate finds; and a termi
arXiv:2608.13698v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric. We conduct a large-scale empirical study of multilingual and non-English GRPO across a wide range of base models, training languages, and different reasoning language rewards. We find that training to reason in the native language often leaves only a small gap to training for English reasoning. We further observe strong crosslingual transfer: training in one language often improves performance in many others. However, specific trends are highly model- and language-dependent. In some cases, training in a particular language induces severe regressions on out-of-domain capabilities in other languages. Our analysis shows that RLVR beyond English can provide broad crosslingual g
arXiv:2608.13624v1 Announce Type: new Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, raising concerns about fairness across demographic subgroups. Fairness evaluation in spoken-input settings is challenging due to confounding factors, including semantic variation in spoken content and speaker-specific characteristics. Ignoring these factors can result in misleading conclusions about model bias. We propose a semantic-aware mixed-effects regression framework for fairness evaluation in LALMs that explicitly accounts for these confounders. Our approach incorporates sentence-level semantic embeddings of reference text as covariates and models speaker identity as a random effect. Notably, semantic representations are extracted from the same LALM under evaluation, enabling semantic control over variation as perceived by the model itself. Experiments on simulated data and real-world b
arXiv:2608.13588v1 Announce Type: new Abstract: Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation systems with lengthy and noisy contexts, thereby undermining both efficiency and accuracy. While existing prompt compression methods attempt to address this issue, they are typically designed for single-turn queries and fail to capture interdependent reasoning steps. We propose IterCOMP, a unified, training-free prompt compression framework that incorporates multi-hop reasoning within an iterative compression loop. IterCOMP decomposes documents into evidence segments, evaluates question answerability, and generates targeted follow-up questions to iteratively integrate essential evidence, producing a compact, reasoning-oriented prompt. Experiments on MusiQue, 2WikiMultiHopQA, and HotpotQA demonstrate that IterCOMP achieves substantial improvements in Exact Match and F1 scores while reducing the to
arXiv:2608.13580v1 Announce Type: new Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive English results. The models obtain leading results among the evaluated open models on OALL2 and AraGen. They also perform strongly on several cultural
arXiv:2608.13578v1 Announce Type: new Abstract: Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent memory architectures, BCMT maintains neither dense interactions between distant tokens nor learned memory states. Its memory mechanism is fully parallelizable and remains compatible with standard impl
arXiv:2608.13571v1 Announce Type: new Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal computed entirely from local inference, which predicts high inflation with AUROC 0.887; and (3) selects models by maximizing a Semantic Exchange Rate
arXiv:2608.13570v1 Announce Type: new Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current methods present a stark trade-off: they either function as unexplainable ''black boxes'' (e.g., Coconut), where the latent reasoning is not human-readable, or rely on separate post-hoc decoders for explainability (e.g., Heima), introducing architectural overhead and decoupling the explanation from the actual reasoning process. In this work, we present a unified framework for Self-Explainable Latent Reasoning (SELR) that trains a single model to perform efficient and inherently explainable latent reasoning. Our core contribution is a novel multi-task training objective that optimizes for two goals simultaneously: (1)
arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary study (Python and TypeScript repos; Claude Opus 4.8, Sonnet 4.6, Haiku 4.5). The answer is conditional and usually negative. On symbol-named localizatio
arXiv:2502.00023v2 Announce Type: replace-cross Abstract: Our research explores the development and application of musical agents, human-in-the-loop generative AI systems designed to support music performance and improvisation within co-creative spaces. We introduce MACAT and MACataRT, two distinct musical agent systems crafted to enhance interactive music-making between human musicians and AI. MACAT is optimized for agent-led performance, employing real-time synthesis and self-listening to shape its output autonomously, while MACataRT provides a flexible environment for collaborative improvisation through audio mosaicing and sequence-based learning. Both systems emphasize training on personalized, small datasets, fostering ethical and transparent AI engagement that respects artistic integrity. This research highlights how interactive, artist-centred generative AI can expand creative possibilities, empowering musicians to explore new forms of artistic expression in real-time, performan
arXiv:2411.13249v2 Announce Type: replace-cross Abstract: Lockdown Mode, introduced in 2022 as an optional security hardening setting for Apple's operating systems, aims to protect users from "some of the most sophisticated digital threats". We present the first academic analysis of Lockdown Mode based on a three-month autoethnographic study of its everyday use. Our findings show that Lockdown Mode does not adhere to most principles proposed by Matthews et al. (2025) for technologies supporting prevention and monitoring of digital threats for at-risk users. Apple provides limited information about the underlying threat model and affected functionality, making it difficult for at-risk users to understand and evaluate the tool. Usability challenges further highlight the need for more granular controls, while the high volume of notifications offers little support for attack detection and instead contributes to user annoyance. Although we consider Lockdown Mode an important step toward imp
arXiv:2604.24448v2 Announce Type: replace Abstract: Mobile health (mHealth) applications support health management through the collection and visualization of rich data, yet the quality of the visualizations varies widely. A key limitation lies in the challenge of effectively visualizing temporally dense, irregular, and context-dependent health data within the constrained mobile interfaces. We argue that this gap is partly driven by a lack of specialized developer tools. Existing libraries primarily target desktop or general-purpose mobile use, providing limited support for health-specific semantics such as normal ranges, thresholds, and goals. As a result, developers often resort to custom solutions that are inconsistent or hard to interpret. We therefore advocate for dedicated mobile visualization libraries tailored to personal health data and mobile contexts, and discuss key design considerations including intelligent defaults, built-in health annotations, and fluid interaction. Suc
arXiv:2608.14400v1 Announce Type: cross Abstract: Bioinformatics workflows rely heavily on visual representations. Quality-control plots, cell embeddings, heatmaps, genome-browser tracks, and interactive dashboards are not merely illustrations, but instruments for making analytical decisions. For blind and low-vision researchers who use screen readers, braille displays, or audio-based interfaces, these create a barrier: the evidence used to justify an analysis is often encoded in visual form, while the underlying decision remains undocumented. We argue that non-visual accessibility and computational reproducibility are closely aligned, as they both require analyses to be transparent and to record why decisions were made. We present ten simple rules for non-visual bioinformatics, covering plots as decision records, cautious use of AI-generated figure descriptions, accessible computing environments, text-first literate programming, structured data and metadata, compact object summaries,
arXiv:2608.14317v1 Announce Type: cross Abstract: This research developed a neural network-based model to extract various information from 2D floor plans. We detect lighting symbols, identify the appropriate type of light, and extract the associated texts with lights. The study aims to enable efficient floor designing and determining the number and type of lights needed per floor, i.e., allow efficient design and estimate the power requirement of the floor plan. The model was developed using Mask RCNN as the base. The images were annotated and converted into a Coco data format for training the model. The model achieved bbox\_mAP and segm\_mAP values of 0.7596 and 0.7111, respectively. It also performed well at different IoU thresholds, i.e., with bbox\_mAP 50 and segm\_mAP 75 values of 0.9850 and 0.9219, respectively. The developed model will help various industries, such as architecture and construction, to improve design time and create efficient workflows by automatically detecting
arXiv:2608.14130v1 Announce Type: cross Abstract: Computer vision models for generated facial content, such as face editing and privacy protection, increasingly affect people, requiring similarity metrics that serve as faithful proxies for human perception. While perceptual evaluation has progressed from signal-based heuristics to representation-based metrics, current approaches are limited to behavioral modeling without cognitive alignment. They rely on implicit and spurious relations while assuming a universal observer, failing to account for inherent variations across diverse human populations. This leads to inaccurate evaluative models of stakeholders and misleading guidance for generative model debugging. Rather than treating perception as a black box, we leverage scientific findings from cognitive psychology of human face similarity perception: dependence on facial featural and configural attributes, nonlinear psychophysical response scaling, and own-group biases. We introduce th
arXiv:2608.13884v1 Announce Type: cross Abstract: The rapid adoption of AI coding assistants and autonomous agentic development systems has coincided with major changes in the pace and structure of open-source software engineering. Yet empirical longitudinal evidence of these changes at the team level remains limited. We present a descriptive longitudinal analysis of seven engineering metrics: pull request (PR) throughput, cycle time, contributor diversity, PR comment density, merge rate, new-author participation, and PR size. Metrics were computed from all merged PRs in two high-velocity AI infrastructure repositories, vLLM (February 2023-June 2026; 18,290 PRs) and SGLang (January 2024-June 2026; 14,938 PRs). We segment development into four eras aligned with major changes in AI-assisted software development and examine human- and bot-authored activities. Both projects show substantial increases in development velocity and AI-developer collaboration signals. PR throughput increased 21
arXiv:2608.13724v1 Announce Type: cross Abstract: PLAUD (Performative Latents and Unsupervised DDSP) is a neural synthesizer and Max for Live instrument for live electronic music, built on NoiseBandNet and trained on small personal sound corpora. We present its architecture, combining a variational DDSP synthesis model, latent smoothing, multi-scale spectral and adversarial losses, and an optional transformer prior, alongside a set of bending operations that intervene directly in the synthesis chain: component limiting, waveshaping, and prior feedback. The Max for Live interface exposes control generation, trajectory sampling, and modulation as primary modes of interaction. Throughout, we thread an affordance analysis arguing that the system's performative character follows from architectural decisions rather than being designed on top of them. The paper contributes both a technical account of the system and a situated affordance analysis of its role in live electronic music performanc
arXiv:2608.13604v1 Announce Type: cross Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from real-time, in-person interaction and is increasingly handled by AI-mediated channels. This shift cuts communicators off from the resources repair depends on faster than new means of detection are being built. In this paper we analyse misunderstanding as a layered process in which a divergence is generated, may then be amplified, and is either detected and repaired or left to persist unnoticed. Consolidating accounts from nine fields of research that do not ordinarily cite one another, we identify eleven exact failure modes and show that each operates at a specific point in a communicative process rather than anywhere within it. Those points give eight analytical layers, derived from the literature rather than adopted from an existing model. Eight of the mechanisms primarily generate a divergence, two primarily amplify one already presen