# Research Papers — 2026-05 · bundle page 44 of 326

> Full-text markdown of papers #2151–2200 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/44
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/43.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/45.md)

### Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits

Authors: Sixue Xing, Haoyu He, Kerui Wu, Zhuo Yang, Haozheng Luo, Tianfan Fu, Aarthy Nagarajan
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2605.29268v3

LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many runs and leave the run-to-run distribution undocumented. We ask how a fixed budget of LLM calls should be allocated, and how reliably a single run reaches the reported numbers. Sweeping the depth-breadth grid over five models and three tasks, we identify two empirical regularities: a fitness-compute envelope along which capability ordering largely collapses when measured in effective FLOPs, and a bilinear depth-breadth fit with task-specific interaction; both are gated by model-task capability. Motivated by these regularities, we propose BaSE (Bandit-based Self-Evolving), a multi-armed bandit that allocates LLM calls across parallel trajectories. Without changing the model, prompt, or evaluator, BaSE improves mean fitness by 12.3% over the strongest island-protocol baseline across 8 (model, task) cells, with the largest gains on high-variance settings: a reliability gain from allocation alone.

---

### Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits

Authors: Sixue Xing, Haoyu He, Kerui Wu, Zhuo Yang, Haozheng Luo, Tianfan Fu, Aarthy Nagarajan
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2605.29268v2

LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many runs and leave the run-to-run distribution undocumented. We ask how a fixed budget of LLM calls should be allocated, and how reliably a single run reaches the reported numbers. Sweeping the depth-breadth grid over five models and three tasks, we identify two empirical regularities: a fitness-compute envelope along which capability ordering largely collapses on effective FLOPs, and a bilinear depth-breadth fit with task-specific interaction; both are gated by model-task capability. Motivated by these regularities, we propose BaSE (Bandit-based Self-Evolving), a multi-armed bandit that allocates LLM calls across parallel trajectories. Without changing the model, prompt, or evaluator, BaSE improves mean fitness by 12.3% over the strongest island-protocol baseline across 8 (model, task) cells, with the largest gains on high-variance settings: a reliability gain from allocation alone.

---

### When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop

Authors: Yang Zhang, Xiukun Wei, Xueru Zhang
Published: 2026-05-28
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.29267v1

Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consuming training paradigm can lead to model collapse, divergence, or bias amplification. Recent work (Ferbach et al., 2024) shows that incorporating human curation into the loop can steer a self-consuming model toward human-aligned behavior, but these analyses focus on a single, isolated model that solely consumes its own outputs. In practice, however, models often interact and train on input-output pairs produced by other models. This paper studies self-consuming training in the multi-model regime. We first formalize a framework for interacting self-consuming models and characterize when the resulting dynamical system converges to a stable point. We then examine how human curation of one model affects its own alignment (self-influence) and how such effects propagate to other models (cross-influence). Unlike isolated settings where human curation always enhances model alignment, we show that cross-model interactions can dampen or even invert this effect, ultimately degrading long-term alignment.

---

### Prior-Guided Frequency-Calibrated Virtual EEG Channel Inference from Four Frontal Electrodes for Wearable EEG Augmentation

Authors: Minghao Xiao
Published: 2026-05-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.29263v3

Low-channel wearable electroencephalography (EEG) is attractive for long-term monitoring, but four frontal electrodes provide only a sparse and spatially biased sampling of the scalp potential field. Virtual-channel methods should therefore be framed not as recovery of independent unmeasured brain activity, but as prior-guided conditional inference of posterior predictive scalp-potential representations at target electrode locations. We present FAVC-Net, a compact frequency-calibrated virtual-channel inference network that estimates 13 target channels from Fp1, Fp2, F7, and F8. The model combines shared multi-scale source encoding, source-state embeddings, target-conditioned signed source-block mixing, GATv2-based attention refinement, attention-consistent skip fusion, and weak Welch power spectral density calibration. The generator is trained as a task-agnostic reconstruction module, without class-label, classification, or CSP-like discriminative constraints, so that the virtual montage remains tied to conditional scalp-potential estimation rather than to a specific downstream decision. On the PRED+CT dataset, FAVC-Net achieved the best joint waveform-spectral operating point among neural and interpolation baselines. Its time-domain gains were modest, whereas log-spectral distance and PSD KL divergence were reduced by 30.50% and 38.94% relative to the strongest non-FAVC comparator. Under wearable-like source perturbations, the model preserved spectral fidelity and channel-frequency texture, with anti-collapse benefits most evident under EMG-like bursts and mixed stress. These results support virtual EEG channels as montage-compatible, frequency-calibrated posterior predictive representations derived from sparse frontal measurements, not as independent substitutes for physically recorded electrodes.

---

### Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling

Authors: Shijie Cao, Yuan Yuan, Jing Liu
Published: 2026-05-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.29262v1

The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimization of production goals. Conventional priority rules are insufficiently flexible to handle complex disruptions, whereas learning-based approaches often compromise interpretability or fail to generalize across problem scales. Although Large Language Models (LLMs) offer advanced reasoning capabilities to bridge this gap, their substantial inference latency is incompatible with the millisecond-level decision cycles of industrial control systems. To resolve this conflict, we introduce RACE-Sched, an asynchronous agent-based framework that decouples policy execution from logical reasoning via a dual-stream architecture. The Reactive Stream executes low-latency symbolic heuristics to enable real-time dispatching, while the parallel Deliberative Stream leverages an LLM to synthesize, validate, and evolve these rules. Candidate rules undergo rigorous testing in a sandbox and are deployed via atomic updates, ensuring safety without blocking the control loop. Additionally, a semantic rule repository indexes validated heuristics for retrieval-based initialization which enhances transferability across problem scales. Extensive evaluations on GEN-Bench, MK-Bench, and JMS-Bench demonstrate that RACE-Sched outperforms leading Deep Reinforcement Learning and other LLM-based baselines. This approach harmonizes real-time constraints with long-horizon reasoning to achieve superior solution quality and robust adaptation to dynamic events.

---

### Deep Psychovisual Image Representations

Authors: Wendi Ma, Aryaman Sharma, Wei Dai, Shekhar S. Chandra
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29260v2

Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In contrast, deep learning-based vision models routinely extract and aggregate features using homogeneous stacks of spatial layers, rendering their decision-making processes opaque. In this paper, we propose Deep Visual Coding, a learned frequency-domain representation inspired by 1990s image codes that quantised perceptually salient frequencies, which together with complex-valued image representations produces psychovisual-style abstractions. This approach enables the first psychovisual-based deep learning framework, utilizing data-driven spectral filters that learn to encode task-relevant semantic structures within distinct frequency sub-bands. Salience analyses reveal that our psychovisual models extract highly interpretable object parts compared to the amorphous regions produced by regular Convolutional Neural Networks (CNNs). Furthermore, we find that our models are less depth dependent than CNNs for model scaling, since our complex-valued representations and learned abstractions subsume the role of the deep spatial layers. Together, these findings demonstrate that psychovisual coding provides a promising path toward more efficient and transparent vision models.

---

### KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs

Authors: Debopam Sanyal, Anantharaman Iyer, Alind Khare, Trisha Jain, Akshay Jajoo, Myungjin Lee, Clayton Kerce, Alexey Tumanov
Published: 2026-05-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.29259v1

Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work demonstrates that stitching pretrained models within a model family enables cost-effective interpolation of the accuracy-efficiency tradeoff space. Stitching transforms intermediate activations from one pretrained model into another, producing a new interpolated stitched network. Such networks provide a pool of deployment options along the accuracy-efficiency spectrum. However, existing stitching approaches often yield suboptimal tradeoffs and lack generalizability, as they primarily rely on heuristics to select stitch configurations. We argue that constructing improved accuracy-efficiency tradeoffs requires explicitly capturing and leveraging the similarity between pretrained models being stitched. To this end, we introduce KLAS, a novel stitch selection framework that automates and generalizes stitch selection across model families by leveraging KL divergence between intermediate representations. KLAS identifies the most promising binary stitches from the $O(k^2n^2)$ possibilities for $k$ pretrained models of depth $n$. Through comprehensive experiments, we demonstrate that KLAS improves the accuracy-efficiency curve of stitched models at the same finetuning cost as baselines. KLAS achieves up to $1.21\%$ higher ImageNet-1K top-1 accuracy at the same computational cost, or maintains accuracy with a $1.33\times$ reduction in FLOPs.

---

### DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents

Authors: Rongsheng Zhang, Jiji Tang, Junnan Ren, Zuyi Bao, Weijie Chen, Ruofan Hu, Zhou Zhao, Tangjie Lv, Yan Zhang
Published: 2026-05-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.29256v1

Role-playing with large language models is fundamentally a session-level task, requiring agents to sustain character identity and interaction quality across extended multi-turn conversations. Yet existing evaluation and optimization methods remain largely turn-level, failing to capture long-horizon quality. We propose DynSess, a unified session-level framework for role-playing agents. DynSess-Eval scores complete dialogue sessions via rubrics targeting long-horizon behaviors. Leveraging its session-level rewards, we construct high-quality training trajectories through multi-turn lookahead search and train DynSess-Character with two complementary variants: DSPO (off-policy) and GSRPO (on-policy). Experiments show that DynSess-Eval aligns with human judgments substantially better than prior evaluators, and blind human evaluation further shows that DynSess-Character matches the strongest character model despite using substantially fewer parameters, while maintaining strong role consistency and interactive ability. Our dataset and code will be released to facilitate future research.

---

### Extreme dynamic symmetry enables omnidirectional and multifunctional robots

Authors: Jiaxun Liu, Boxi Xia, Boyuan Chen
Published: 2026-05-28
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2605.29254v1

Symmetry is a central organizing principle in natural systems, yet its use as a unifying design strategy in robotics has largely remained limited to geometric form. We show that symmetry can instead be leveraged at the level of dynamic actuation capability. We introduce dynamic symmetry, the uniformity of a robot's attainable center-of-mass accelerations, and formalize it through a measure coined as dynamic isotropy. Across more than 1000 simulated morphologies, we found that higher dynamic symmetry consistently improved trajectory tracking, task success, robustness, resiliency, and energy efficiency, with the benefits becoming most pronounced as dynamic isotropy approached its theoretical limit. To study this regime systematically, we developed Argus, a family of spherical robots designed to explore the effects of increasing dynamic symmetry. Members of the Argus family vary in their actuation geometry and dynamic symmetry level while sharing a common architectural principle: radially oriented linear actuators that directly shape the robot's center-of-mass dynamics. Among them, we built a physical 20-leg Argus variant that achieved near-extreme dynamic isotropy and demonstrated orientation-invariant locomotion, agile traversal of cluttered and deformable terrain, rapid self-stabilization, and resilience to partial actuator failures. Its distributed sensing further enabled omnidirectional perception and object interaction during continuous motion. These results show that designing robots for symmetry not only in morphology but also in their attainable dynamics provides a powerful and general pathway toward agility, robustness, and multifunctionality in uncertain terrestrial and extraterrestrial environments.

---

### OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

Authors: Yibing Liu, Yangze Liu, Xiaolong Yin, Bin Wang, Chong Zhang, Hao Yin, Zhongyi Han
Published: 2026-05-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.29253v1

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task-oracle outcomes with structured process evidence. FullTax converts the aligned trajectories into structured anomaly supervision: binary labels, supporting evidence, onset/span localization, severity, recoverability, and a 5-class anomaly taxonomy. Using OpenClawBench, we make the Outcome-Process Gap measurable. Among 31,135 oracle-passing executions, 2,904 are still labeled process-anomalous under FullTax. These results show that success-only evaluation misses a concrete class of process-side failures in real agent executions. A LoRA-fine-tuned Gemma 3 12B detector trained on the high-confidence FullTax supervised pool reaches binary F1=0.729 on the cleaner-labels held-out test split. Together, OpenClawBench turns real agent execution logs into auditable and reusable supervision for studying, diagnosing, and operationally monitoring runtime agent reliability.

---

### Provably Secure Agent Guardrail

Authors: Benlong Wu, Weiming Zhang, Kejiang Chen, Han Fang, Nenghai Yu
Published: 2026-05-28
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2605.29251v1

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures heavily rely on empirical semantic guardrails and probabilistic large model adjudicators, mechanisms that fail to provide deterministic security lower bounds when facing complex semantic symbol decoupling attacks. To overcome this empirical semantic guardrail dilemma, this paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning. Based on this paradigm, we further introduce an executable Proof-Constrained Action (ePCA) framework with a neural symbolic isolation architecture. This framework abandons semantic trust in natural language, forcing agents to losslessly formalize their intentions into first-order logical mathematical constraints before performing physical operations. Empirical evaluations of macroscopic and microscopic two-dimensional dynamic adversarial systems demonstrate that our formal verification mechanism achieves zero attack success rate and zero false positive rate across the evaluated scenarios, with extremely low computational latency. This research provides a conditional formal foundation under explicit system assumptions and an engineering paradigm for constructing the underlying defense foundation for future intelligent systems.

---

### OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Authors: Jinheon Baek, Soyeong Jeong, Sangwoo Park, Woongyeong Yeo, Minki Kang, Patara Trirat, Heejun Lee, Sung Ju Hwang
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2605.29250v1

Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces. A natural attempt at unification would collapse these sources into a shared space, but this erases the structural affordances (such as schemas, ontologies, compositional operators) that give each source its expressive power. Effective retrieval over diverse knowledge, therefore, requires not homogenization but an overarching layer that meets each source on its own terms. To achieve this, we present OmniRetrieval, a framework that takes any natural-language query, identifies appropriate knowledge sources, and dispatches source-native queries to their native execution engines. Across an extensive benchmark spanning 13 datasets and 309 distinct knowledge bases over text, relational, and graph-structured sources, OmniRetrieval exceeds single-source baselines, demonstrating that it can serve as a general-purpose interface to the heterogeneous sources while preserving the structural distinctions that make each source valuable.

---

### Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research

Authors: Nicolas Emmenegger, Ellery Stahler, Chara Podimata
Published: 2026-05-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2605.29249v1

Many applications require statistically valid inference across many related tasks, while using only a handful of high-quality labels per hypothesis. In AI evaluation, these tasks may correspond to model behaviors across prompts, subgroups, or hypotheses; in social science surveys, they may correspond to related questions, populations, or measurement conditions. Prediction-powered inference (PPI) uses abundant but inexpensive proxy measurements to improve inference from limited, ground-truth labels, but commonly used methods treat tasks independently and therefore fail to exploit shared structure across related tasks. This limitation is especially important in settings where only a small number of labels are available per task. To address this issue, we introduce a multi-task prediction-powered inference framework that uses labeled data from related tasks to improve power while preserving task-specific inference. Our methods exploit the shared structure in the proxy-ground-truth relationship through cross-task recalibration, while retaining within-task rectification and power tuning to construct accurate point estimates and confidence intervals. We prove that efficiency gains beyond power-tuned PPI are only possible when the proxy-ground-truth relationship contains nonlinear structure; affine cross-task recalibrations are asymptotically equivalent to using the original proxy. We complement our theoretical findings with experiments on synthetic and semi-synthetic datasets, as well as a case study auditing language models on election-related information during the 2024 U.S. presidential election. Using a large human-annotation study, we show that cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.

---

### DenseSteer: Steering Small Language Models towards Dense Math Reasoning

Authors: Yang Ouyang, Shuhang Lin, Jung-Eun Kim
Published: 2026-05-28
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.29247v1

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model family on math reasoning benchmarks, we find that more proficient reasoning is associated with fewer reasoning steps but higher information density per step, a property we term Dense Reasoning. Motivated by this observation, we propose DenseSteer, a training-free inference-time steering framework that enhances small-model reasoning by modulating internal representations toward dense reasoning patterns. Experiments show that our method yields consistent accuracy improvements without increasing token-level Negative Log-Likelihood, highlighting dense reasoning as an effective structural approach to mathematical problem solving.

---

### Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

Authors: Bing Liu, Shunping Wang, Yufan Zhu, Xinyi Yu, Jing Huang, Linkang Du, Hongbin Pei, Wei Luo
Published: 2026-05-28
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2605.29245v2

This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial investments in data, computation, and expertise, and are increasingly deployed in high-stakes settings, making it critical to protect LLM-related assets and trace their origins. Existing work has rapidly expanded across dataset provenance, model ownership, and generated-content detection, but the field remains fragmented: fingerprinting and watermarking are often used inconsistently, and methods are typically studied within isolated asset-specific settings. To address this gap, we introduce implicit identity as a unifying abstraction for verifiable but not directly observable identity signals in LLM systems. We distinguish fingerprinting as non-intrusive identity derived from intrinsic characteristics, and watermarking as intrusive identity deliberately embedded into data, models, or generated content. We then propose a lifecycle-based taxonomy that organises techniques across datasets, models, and generated content, and further separates them by verification semantics: similarity-based attribution and keyed verification. Finally, we establish an evaluation framework centred on identifiability, robustness, and deployability, summarising representative metrics under realistic access and transformation regimes. By unifying terminology, lifecycle stages, and evaluation objectives, this survey provides a structured foundation for studying LLM identity technologies and for developing more reliable mechanisms for asset protection and provenance.

---

### Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment

Authors: Laerdon Kim, Vivian Nguyen, Cristian Danescu-Niculescu-Mizil
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2605.29243v1

Forecasting conversational derailment is the task of predicting, as the conversation unfolds, whether it will eventually derail into personal attacks. Since forecasting models operate in an online fashion, they must decide whether to "trigger" an alert after each utterance--for example, to notify participants or a moderator that the conversation is at risk of derailing. Existing approaches make this decision solely based on the estimated likelihood of derailment given the preceding utterances, implicitly assuming that the conversation's future trajectory is fixed. As a result, they ignore the possibility of future recovery and incur an unnecessarily high rate of false positives. In this work we propose a method for decoupling the decision to trigger from derailment likelihood estimation. Our approach is inspired by the first human baseline on this task, which shows that humans achieve dramatically lower false positive rates by selectively deferring their decision to trigger when they anticipate that tension is likely to subside. We operationalize this insight with a deferral mechanism that uses forward-looking simulations to assess whether a tense moment admits plausible paths to recovery. Incorporating this mechanism into a state-of-the-art forecasting model substantially reduces false positives without sacrificing forecasting accuracy. More broadly, this work highlights the value of treating decision-making as a first-class component of forecasting systems.

---

### Surfacing Isolated Learners with Outcome-Independent Mediation of Feedback between Teachers and Students Using AI

Authors: Junsoo Park, Youssef Medhat, Htet Phyo Wai, Ploy Thajchayapong, Ashok K. Goel
Published: 2026-05-28
Categories: cs.AI, cs.CL, cs.HC, cs.IR
arXiv: https://arxiv.org/abs/2605.29240v1

AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to translate into timely instructional decisions. We propose an interpretable decision layer: a transparent mechanism that ranks course topics requiring attention without using grades or post-hoc outcome labels. The approach combines three signals: student learning difficulty prevalence, disagreement between learner self-reports and observed difficulties, and unresolved teacher concerns. The output is a ranked set of topic priorities with per-topic decision records explaining each ranking. In one graduate CS course offering ($n=5$ instructor interviews; $n=279$ survey responses), prioritized topics aligned with instructor concerns (top-5 overlap 3/5; Spearman $ρ=0.80$) and student-reported topic difficulty ($ρ=0.46$, $p=.048$). Multi-signal integration also surfaced learners not identified through individual signal sources alone (AUC $=0.96$ vs. $0.91$ for gap prevalence alone). Reflective thinking, help-seeking, and self-efficacy provided additional evidence that student behavioral signals align with learning-related constructs. While preliminary, these findings suggest that transparent coordination mechanisms may help support human-AI co-agency when feedback is incomplete.

---

### SigmaMedStat: Temporal Signal Modeling for ICU False Alarm Reduction

Authors: Arunkumar Ramachandran
Published: 2026-05-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.29236v1

Alarm fatigue in intensive care units (ICUs) is a well documented patient safety crisis. Clinical monitors generate 350 or more alarms per patient per day, out of which 72-99% are clinically irrelevant. Staff desensitization to non-actionable alarms increases the risk of missed true emergencies. This paper presents SigmaMedStat, a machine learning system that evaluates the trustworthiness of physiological alarm signals before clinical action is taken. Four approaches were evaluated on the PhysioNet/Computing in Cardiology Challenge 2015 dataset of 498 four-channel ICU alarm recordings. Primary contribution is a temporal modeling framework that splits each 60 second recording into six consecutive 10-second chunks, and this in turn generates Continuous Wavelet Transform (CWT) scalograms per chunk, encodes each chunk with a shared EfficientNet-B0 encoder, and passes the resulting feature sequence to a two-layer Long Short-Term Memory (LSTM) network. Five-fold stratified cross-validation yields a mean AUC of 0.822 +/- 0.016 (95% CI: (0.790,0.853)), compared to 0.641 for a static EfficientNet baseline trained on the full 60-second window. Ablation studies confirm that temporal chunking and multi-channel signal fusion both contribute independently to classification performance. Per-alarm type analysis reveals that Ventricular Flutter is the most accurately classified alarm type (AUC 0.820) while Asystole remains the hardest (AUC 0.722). Error analysis identifies 65 false negatives and 85 high-confidence misclassifications as the primary failure modes. All code and results are publicly available at https://github.com/Arun-K-Ram/sigmamedstat.

---

### Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground Truth

Authors: Gaurav Sahu, Laurent Charlin, Christopher Pal
Published: 2026-05-28
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2605.29234v1

We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as an evaluation target. First, we implement a Deep Research pipeline that processes the full query paper and expands the retrieved results breadth-first along their bibliographies, and show that it substantially outperforms vanilla API-only search, raising recall on RollingEval-Jun25 (a 250-paper literature-search benchmark) from below 20% to above 80%. Second, we use a neutral LLM-as-a-judge to determine if human references are sound ground truth for the task. We find significant limitations: only 51% of human citations are judged moderately relevant or higher, against 86--88% for the strongest AI-based re-rankers. We study this gap on the OpenAlex co-authorship graph, finding that humans are 2.5x more likely than the best AI re-rankers to cite a direct collaborator. Together, our results argue against single-axis literature-search evaluation: recall, topical-relevance scoring, ranked-list diversity, and a co-authorship-distance diagnostic each measure complementary properties of citation quality and should be reported jointly.

---

### BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

Authors: Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji, Yong Liu, Yingyan Celine Lin
Published: 2026-05-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.29233v2

Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding. In practice, however, block-wise dLLM inference exposes a difficult granularity trade-off: small blocks preserve local conditioning but require many denoising steps, whereas large blocks expose more parallelism but can make premature commitments and accumulate cache error. Existing acceleration methods typically choose a single block size per request, leaving the complementarity among block sizes unused. We show that block size itself is a useful branching dimension. Different block sizes induce related but non-identical KV-cache trajectories: branches often share an initial prefix, bifurcate at semantically decisive positions, and later agree on syntactically lightweight tokens. Motivated by this structure, we propose BlockBatch, a training-free online inference framework that executes multiple block-size branches for the same request inside a batched forward pass. BlockBatch coordinates these branches through confidence-gated token merging, leader-based synchronization, and periodic full-sequence refreshes that re-anchor local block updates to a globally consistent KV state. Across 3 representative dLLMs and 4 datasets, BlockBatch reduces denoising NFEs by 26.6\% on average and achieves a 1.33$\times$ average end-to-end speedup over Fast-dLLM while preserving accuracy. These results identify block-size diversity as a practical and previously underexplored axis for branch-parallel dLLM inference.

---

### Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data

Authors: Caio Petrucci, Leo Sampaio Ferraz Ribeiro, Sandra Avila
Published: 2026-05-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2605.29230v2

Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises ethical, legal, and privacy concerns and that child-data governance frameworks explicitly advise against. While the task remains relevant (e.g., for detecting child sexual abuse imagery), we advocate against using data from minors entirely and quantify what the exclusion costs in accuracy. We formalize age estimation without children's training data as a generalized zero-shot learning (GZSL) problem: age intervals present during training are seen classes and withheld intervals are unseen, with models evaluated jointly on both. The generalized setting, rather than conventional zero-shot evaluation on unseen classes alone, is the appropriate one here because a deployed estimator must operate across the entire lifespan, not only on the interval withheld from it. Revisiting six widely used datasets, we introduce standardized splits with strict age-group separation. For datasets with identity annotations, subject-age-exclusive splits prevent identity leakage across the seen/unseen boundary. Evaluating nine state-of-the-art age estimation methods under this protocol reveals that all of them fail to generalize to unseen age groups, suffering substantial degradation --- on average 46.4%, and up to 52.8% --- relative to the supervised baseline. Moreover, models do not simply degrade: they systematically anchor predictions for unseen ages to nearby seen classes, a manifestation of the well-known seen-class bias in generalized zero-shot learning.

---

### Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility

Authors: Jiahao Huang, Fei Cheng, Junfeng Jiang, Akiko Aizawa
Published: 2026-05-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.29229v1

Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces the Data-Model Compatibility (DMC) metric, which can be used to assess the suitability of a dataset for reasoning distillation on a student model. DMC provides an assessment by jointly considering data quality, relative difficulty, and student capability. We validated the effectiveness of DMC from two perspectives: (1) DMC exhibits a strong correlation with reasoning distillation performance; and (2) using DMC as the criterion for data selection leads to improved reasoning distillation performance. Both findings are consistently demonstrated across multiple student models and tasks. Moreover, since the DMC of each dataset dynamically changes during training, our experiments demonstrate that dynamically selecting datasets based on DMC can further enhance performance.

---

### Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification

Authors: Aydin Wells, Francis A. Gatsi, Aaron Striegel, Tijana Milenković
Published: 2026-05-28
Categories: cs.LG, q-bio.MN
arXiv: https://arxiv.org/abs/2605.29228v2

Protein structure classification (PSC) uses supervised learning to predict a protein's CATH/SCOP(e) class from the protein's sequence or 3D structural feature(s). We already modeled 3D structures as (static) protein structure networks (PSNs), demonstrating the competitiveness of PSN-based features to sequence or direct (i.e. non-network) 3D structural features in the PSC task. More recently, we demonstrated the power of features extracted from dynamic PSNs over features extracted from static PSNs (and thus by transitivity over sequence and direct 3D structural features) in the same task. That dynamic PSN approach used traditional machine learning (ML), combining manual (pre-engineered) features with an off-the-shelf classifier. Here, we evaluate whether automatic deep learning (DL) from the dynamic PSNs yields improvements. Our evaluation on 72 datasets spanning ~44,000 CATH- or SCOPe-labeled dynamic PSNs reveals that in terms of PSC accuracy, traditional ML and DL are (close to) tied for a large majority of the datasets, while DL is on average 10+ times slower. We are the first to evaluate traditional ML vs. DL in the dynamic PSN-based PSC task.

---

### BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Authors: Jiahao Huang, Fei Cheng, Junfeng Jiang, Zefan Yu, Akiko Aizawa
Published: 2026-05-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2605.29225v1

Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no mechanism to target specific failure patterns. We present \textbf{BenchTrace}, a benchmark for evaluating self-evolution ability in LLM agents. BenchTrace is built on a snapshot-reflection dataset of 1,821 annotated episodes spanning six diverse tasks, and comprises a \textbf{Reflection Evaluation} that probes failure identification through targeted QA tasks, and an \textbf{Evolution Evaluation} that tests whether past failure experience translates into avoidance behavior in a controlled self-evolution simulation. Building on BenchTrace, we propose \textbf{failure avoidance rate (FAR)}, a new evaluation metric measuring the fraction of test cases in which the agent successfully avoids the target failure instance. Experiments with Qwen3-32B and GPT-4.1 reveal that both models fall below a 30\% end-to-end pass rate on reflection evaluation, with diagnosis as the primary bottleneck. Evolution evaluation shows that self-evolution methods generally improve FAR over the non-evolving baseline, but agents forget early lessons as noise episodes accumulate, and agents fail to generalize their reflections beyond the specific context, causing negative transfer across task contexts. Our correlation analysis further reveals that only a fully correct reflection is strongly associated with higher FAR. BenchTrace exposes concrete limits of current self-evolution approaches and provides a controlled, model-agnostic framework for targeted evaluation.

---

### Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

Authors: Aditya Nawal, Manit Baser, Mohan Gurusamy
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2605.29224v2

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

---

### Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

Authors: Aditya Nawal, Manit Baser, Mohan Gurusamy
Published: 2026-05-28
Categories: cs.CL, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2605.29224v1

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

---

### Inferring the Size of Large Language Models From Popular Text Memorization

Authors: Ivica Nikolic
Published: 2026-05-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.29223v3

The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary reference point for interpreting capabilities and costs -- largely undisclosed. We propose a black-box method to infer conservative lower bounds on LLM size from generated text outputs alone, requiring nothing beyond the ability to submit text fragments and observe next-token predictions. Our approach is grounded in a key observation: popular, widely-circulated texts -- such as classical literature, religious texts, and foundational documents -- are present in virtually every large-scale pretraining corpus, and how accurately a model predicts the next word across text fragments of varying length is a reliable signal of how much it has memorized them, which in turn is fundamentally limited by its total parameter count. We aggregate this memorization signal across a diverse corpus of texts and fragment lengths into a single accuracy profile vector per model, and build two complementary inference methods on top of it: a pairwise statistical test that determines which of two models is larger, and a scaling-law estimator that extracts a one-dimensional latent index from these vectors via Principal Component Analysis (PCA) to map the aggregated signal to a parameter count. Validated on a broad set of open-weight models, both methods produce accurate and reliable lower bounds. When applied to popular closed-weight models, our framework recovers internal product hierarchies and reveals a clear divergence in industry scaling strategies: while some developers yield significantly higher bounds indicative of large generational parameter growth, others operate under strict parameter ceilings, demonstrating that hidden design choices can be systematically probed even under strict API limitations.

---

### An Approach for Thyroid Nodule Analysis Using Thermographic Images

Authors: J. R. González, É. O. Rodrigues, C. P. Damião, C. A. P. Fontes, A. C. Silva, A. C. Paiva, H. Li, C. Du, A. Conci
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29221v1

Thyroid cancer is said to be the second most common type of cancer in female individuals and the third in males by 2030, according to projections. In general, detecting cancer in its early stages improves the chance of survival of the individual. Thermography is a diagnostic tool that has been increasingly used to detect cancer and abnormalities, including that of thyroid. Various methods to segment and detect hot regions in thermograms and, consequently, to detect suspicious tissues present in these images have been proposed. It is well known that medical diagnosis yields a great deal of information. Thus, physicians have to comprehensively analyse and evaluate this information in a short period of time, which is infeasible in most cases. In this work, we perform a general review of thermography , focusing on the thyroid analysis. We propose protocols for image acquisiton and an autonomous registration for thyroid images. We also perform analyses of the image data, which include feature extraction, image processing, and a possible approach for classification of healthy or unhealthy patients. In summary, this work presents a pilot project for detection of tumors in our university hospital, which is part of an effort to support preventive medical actions in our endocrinology department. Under some future adjustments, this project will be submitted for approval by the ethics and research committee of Hospital Universitário Antonio Pedro at Universidade Federal Fluminense (HUAP-UFF) and to the Brazilian Ministry of Health Ethical committee under the name: Evaluation of the importance of thermography to aid diagnosis of thyroid nodules of patients in HUAP-UFF (in Portuguese: Avaliação da importância da termografia no auxílio à investigação diagnóstica de nódulos tireoidianos em pacientes acompanhados no HUAP-UFF).

---

### Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes

Authors: Leonidas Zimianitis, Pasindu Thenahandi, Kai Buckhalter, Dineth Jayakody, Julian O. Kimura, Xinyue Liang, Karen Cunningham, Azeem Ahmad, Balpreet S. Ahluwalia, Sampath Jayarathna, Nikos Chrisochoides, Brandon Weissbourd et al.
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29220v1

Tracking the dynamics of non-canonical biological systems in microscopy videos remains a persistent challenge. Both classical and learning-based trackers depend on expert-reviewed data to be evaluated and adapted, yet exhaustive manual annotation rarely scales to the videos where these tools are needed most. We developed RIPPLE (Refinement Interpolation Platform for Point Location Estimation), which recasts annotation as sparse correction: a user clicks a starting point, RIPPLE proposes a full trajectory, and the user intervenes only where the trajectory drifts. We tested RIPPLE on five challenging microscopy datasets from our laboratories, four from the transparent jellyfish Clytia hemisphaerica and one tracking landmarks on rapidly moving sperm. Across these, RIPPLE matched the quality of exhaustive manual annotation while reducing manual clicks by 3 to 25 times across datasets. RIPPLE thereby fills a missing layer between manual annotation and fully automated tracking, enabling immediate quantification of biological dynamics, method benchmarking, and the production of the gold-standard data needed to adapt future automated microscopy trackers.

---

### SalsaAgent: A multimodal embodied language model for interactive dance generation

Authors: Payam Jome Yazdian, Zoe Stanley, Angelica Lim
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29219v3

Embodied interaction with humanoids depends on bidirectional nonverbal reactivity, coordination, and synchrony to convey cues and move with a partner. For socially interactive embodied agents, reactive motion generation requires expressive full-body motion that remains contextually appropriate while maintaining spatial and temporal synchrony. We present SalsaAgent, a language model that generates expressive, full-body salsa follower motions in reaction to a human leader and music. We formulate partner interaction as nonverbal token passing, extending the vocabulary of a large language model (LLM) to process discrete motion tokens, pairwise relation tokens, and audio tokens. Our method introduces full-body and pairwise-relation tokenizers, aligns language and motion tokens with automatically derived text descriptions of skeleton dynamics, and applies a two-stage token-to-diffusion pipeline. Subjective and objective evaluations show improved motion quality, two-person spatial coordination, and music and partner coordination relative to prior baselines.

---

### SalsaAgent: A multimodal embodied language model for interactive dance generation

Authors: Payam Jome Yazdian, Zoe Stanley, Angelica Lim
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29219v2

Interaction between humanoids involves bidirectional and nonverbal reactivity, coordination and synchrony. Toward socially aware robots and interactive virtual agents, we present SalsaAgent, a language model that generates expressive, full-body salsa dance motions in reaction to a human leader and against a contextual music backdrop. We formulate interaction as nonverbal motion token passing, extending the vocabulary of a large language model (LLM) to process discrete motion tokens, pairwise relation tokens, and audio. Our contributions include new tokens for full-body and motion relations, LLM fine-tuning using automatically derived text descriptions of skeleton dynamics for token grounding, and a two-stage token-to-diffusion pipeline. Subjective and objective evaluations demonstrate the effectiveness of our approach in terms of motion quality, music and partner coordination, and consistent two-person spatial behavior, with significant improvements over baselines.

---

### GTA: Generating Long-Horizon Tasks for Web Agents at Scale

Authors: Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu
Published: 2026-05-28
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.29218v1

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that must generalize to realistic, multi-hop, cross-page tasks. We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control to produce realistic tasks paired with executable trajectories. This design decouples crawling from generation for greater efficiency, grounds tasks in the site graph to enforce compositionality, and ensures dense supervision through deterministic replays and systematic validation. We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage. The resulting benchmark reveals a significant human-agent performance gap and enables detailed diagnostics. Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.

---

### Towards the automated segmentation of epicardial and mediastinal fats: A multi-manufacturer approach using intersubject registration and random forest

Authors: É. O. Rodrigues, A. Conci, F. F. C. Morais, M. G. Pérez
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29217v1

The amount of fat on the surroundings of the heart is correlated to several health risk factors such as carotid stiffness, coronary artery calcification, atrial fibrillation, atherosclerosis, cancer incidence and others. Furthermore, the cardiac fat varies unrelated to the overall fat of the subject, and, therefore, it reinforces the quantitative analysis of these adipose tissues as being essential. Clinical decision support systems are computer programs capable of evaluating information and providing a corresponding diagnosis or data to complement the physicists' analyses. The aim of this work is to propose a method capable of fully automatically segmenting two types of cardiac adipose tissues that stand apart from each other by the pericardium on CT images obtained by the standard acquisition protocol used for coronary calcium scoring. Much effort was devoted to promote minimal user intervention and ease of reproducibility. The methodology proposed in this work consists of a registration, which will roughly adjust input images to a standard, an extraction of features related to pixels and their surrounding area and a segmentation step based on data mining classification algorithms that define if an incoming pixel is of a certain type. Experimentations showed that the achieved mean accuracy for the epicardial and mediastinal fats was 98.4% with a mean true positive rate of 96.2%. In average, the Dice similarity index was equal to 96.8%.

---

### MetaRanker: Human-in-the-loop Active Ranking for Metalens Image Quality

Authors: Yujin Park, Haejun Chung, Ikbeom Jang
Published: 2026-05-28
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2605.29212v2

Image quality in modern imaging systems emerges from the coupled effects of the sensor, optics, and computational reconstruction. Ultra-thin metalenses offer a path toward substantial miniaturization of optical modules, but practical designs often exhibit pronounced chromatic and field-dependent aberrations that necessitate computational reconstruction. In current metalens pipelines, reconstruction models are commonly trained and selected using distortion-based fidelity objectives, such as PSNR, yet these proxies can be weakly correlated with human preference and downstream utility, reflecting the well-known perception--distortion trade-off. We introduce MetaRanker, a human-in-the-loop active ranking framework that formalizes metalens image quality in terms of semantic interpretability, defined as the degree to which humans can reliably recognize objects and structures in the presence of optical artifacts. MetaRanker combines a probabilistic preference model with uncertainty-aware query selection, and leverages vision--language models to provide lightweight semantic priors. Importantly, these priors are used only to guide the sampling of informative comparisons; human judgments remain the primary supervision signal throughout. Across real-world and synthetic metalens datasets with distinct degradation profiles, MetaRanker produces rankings that align most closely with human assessments, while reducing the number of pairwise annotations required by approximately 80% relative to exhaustive pairwise evaluation. Finally, we show that standard image quality assessment metrics exhibit limited alignment with human interpretability in the metalens domain, positioning MetaRanker as a practical step toward perceptually grounded metalens evaluation and co-design.

---

### libhmm: A Modern C++20 Library for Hidden Markov Models with Correct MLE Emission M-Steps

Authors: Gary Wolfman
Published: 2026-05-28
Categories: cs.MS, cs.LG
arXiv: https://arxiv.org/abs/2605.29208v2

We describe libhmm, a C++20 library for Hidden Markov Model parameter estimation, sequence decoding, and model selection. libhmm addresses two gaps in existing software: the absence of a well-maintained, zero-dependency C++ HMM library suitable for embedding in production systems, and the widespread use of method-of-moments (MOM) approximations in the emission distribution M-step of the Baum-Welch algorithm. The library implements correct maximum likelihood estimators for sixteen scalar emission distributions, including an ECME algorithm for the location-scale Student-t distribution, Newton-Raphson maximization for Gamma, Beta, Weibull, and Negative Binomial distributions, and the von Mises distribution for circular data. All forward-backward and Viterbi calculations operate in full log-space. SIMD acceleration is provided for AVX-512, AVX2, SSE2, and ARM NEON via compile-time dispatch with scalar fallback. Version 4 adds multivariate observation support via the BasicHmm<Obs> template, with three multivariate emission families (diagonal Gaussian, full-covariance Gaussian, and independent components) each with correct weighted MLE M-steps. Python bindings are available via the companion package pylibhmm. We compare libhmm against established C and C++ HMM libraries and against published R reference packages on seven real-data benchmarks, and discuss the architectural tradeoffs made in the design.

---

### Auditing Training Data in Generative Music Models via Black-Box Membership Inference

Authors: Yi Chen Liu, Jiawei Yu, Kexin Cao, Syed Irfan Ali Meerza, Trishika Movva, Jian Liu
Published: 2026-05-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.29202v1

Recent advances in text-to-music generation enable high-fidelity synthesis of structured musical audio, raising growing concerns about data provenance, consent, and training transparency. These models are typically trained on large-scale corpora with little disclosure, leaving no practical mechanism to verify whether a particular audio sample was included in training. In this paper, we investigate black-box membership inference for generative music models, aiming to determine whether a candidate music sample was used during training, given only query access to the deployed system. Our key insight is that training membership induces systematically stronger semantic and structural alignment between a candidate sample and the model's generation conditioned on its caption. We query the target model with the associated caption and measure the relationship between the candidate audio and the generated output in a learned feature space. To capture features that separate members from non-members, we construct paired examples consisting of each track and its caption-conditioned generation from shadow models, and train a music auditor to classify membership. The auditor captures alignment patterns characteristic of training membership and generalizes to unseen target models in a fully black-box setting without access to model parameters or training metadata. Across multiple state-of-the-art music generators, our method achieves up to 98.6% accuracy, with false-positive and false-negative rates as low as 1.9% and 1.0%, demonstrating that reliable training-data auditing is feasible in realistic deployment scenarios.

---

### Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization

Authors: Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yuta Kyuragi, Aditya Grover
Published: 2026-05-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.29198v2

Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including mathematical reasoning and text-to-image generation. However, their reliance on sample-level rewards introduces a key limitation as uniform credit assignment across all tokens fails to capture fine-grained, token-level contributions. To address this issue, we propose Guidance Contrastive Policy Optimization (GCPO), a novel algorithm that enables per-token credit assignment by contrasting model predictions under positive and negative prompts. Rather than uniformly broadcasting sample-level advantages, GCPO assigns token-level advantages proportional to the difference between these contrastive predictions, allowing more precise and informative learning signals. Empirically, we find that GCPO emphasizes semantically relevant regions such as visual areas aligned with textual prompts in text-to-image generation, and critical keywords within reasoning traces for chain-of-thought tasks. Through extensive experiments, GCPO consistently outperforms GRPO and DAPO baselines on both text-to-image generation and chain-of-thought reasoning benchmarks, demonstrating its effectiveness as a general and scalable optimization strategy for discrete policy learning.

---

### Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems

Authors: Jules Berman, Tobias Blickhan, Benjamin Peherstorfer
Published: 2026-05-28
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2605.29194v1

Many stochastic physical systems evolve smoothly over time in the sense that the distribution of states changes regularly across time steps. The transition from current state to the next state can often be modeled as the combination of a smooth map and an explicit source of randomness. Stochastic Lifting exploits this structure by attaching an independent, high-dimensional random label to each state transition in the training data and fitting a transition map from the current state and label to the next state using a standard regression loss. The labels act as auxiliary coordinates that let the model represent multiple plausible next states from similar current states, avoiding collapse to a mean prediction in the finite-sample size regime. At inference, fresh labels are sampled at each time step and the learned map is rolled forward autoregressively, generating diverse trajectories with a single network evaluation per time step.

---

### ReasonOps: Operator Segmentation for LLM Reasoning Traces

Authors: Daniel Lee, Owen Queen, James Zou
Published: 2026-05-28
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.29192v1

Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structure. Previous methods developed to analyze chain-of-thought traces are either too rigid or not expressive enough, failing to capture features across domains and models. To remedy this, we develop ReasonOps, an unsupervised, expressive method for annotating chain-of-thought traces, providing succinct universal operators. Using ReasonOps, we analyze 44,662 traces from 12 thinking LLMs spanning 6 families across 8 reasoning benchmarks and discover that they share a common compositional structure: 7 recurring reasoning operators -- discourse-level moves such as backtracking, inferring, and hypothesizing -- that emerge from unsupervised clustering of sentence-initial 3-token pivots. These operators appear across every model family and benchmark domain, confirmed by three independent LLM judges who classify held-out samples at 70 -76% accuracy. We analyze the structure of operators on easy vs. hard problems, revealing that reflective operators are more helpful on hard problems and harm performance on easy problems. Operator sequences are highly model-identifying: a classifier trained on operator distributions alone recovers the source model with macro-AUC, revealing that each model family has a distinctive reasoning fingerprint. Structural operator features predict within-problem answer correctness well above baselines. Classifiers built on these operators reach WP-AUC and on AIME specifically. ReasonOps further enables early quality estimation well before the trace completes: we predict at WP-AUC for only 50% of the trace. The ReasonOps pipeline is unsupervised and annotation-free, enabling deep insights into LLM reasoning traces as well as strong downstream results on model identification and correctness prediction.

---

### When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer

Authors: Mayug Maniparambil, Arjun Karuvally, Terrence Sejnowski, Fergal Reid
Published: 2026-05-28
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.29190v1

Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why it does so -- remain under-explored. We study cross-domain transfer in a 7B model whose SFT and RL post-training stages use only constraint-satisfaction puzzles, with no mathematics problems in the post-training data. To analyze how transfer emerges, we introduce a reasoning primitive-level framework that combines a 9-class span classifier with motif extraction, allowing us to segment chain-of-thought traces into primitive motifs and track their evolution across training stages and domains. We find that puzzle SFT induces a reasoning-primitive vocabulary, yielding a $+7$pp \texttt{pass@32} gain on OlymMATH-Hard. Vanilla GSPO then composes these primitives into longer compute-verify chains, adding a further $+6$pp. However, this RL stage also suppresses exploratory primitives such as \textit{hypothesize} and \textit{backtrack}. To address this, we introduce a novelty bonus that rewards diverse correct rollouts, using perplexity under the reference model as a signal. This restores recovery primitives during RL and adds a further $+7$pp \texttt{pass@32} relative to vanilla GSPO. Finally, the end-to-end recipe raises the hard-math capability ceiling from $16.0\%$ at the OLMo3-7B-Instruct-SFT base to $36.0\%$, without adding any mathematics problems during the SFT or RL stages.

---

### Large Models for Battery Prognostics and Health Management: A Review and Future Roadmap

Authors: Jiale Liu, Huan Wang, Weicheng Wang, Rong Zhu, Qiqi Wang, Min Xie
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.26111v1

Battery Prognostics and Health Management (BPHM) is critical for ensuring the safe, reliable, and cost-effective operation of batteries across electric vehicles, grid storage, and consumer electronics. Conventional BPHM approaches, including physics-based models and task-centric deep learning methods, face challenges in computational efficiency and parameterization, cross-domain generalization, dependence on extensive labeled run-to-failure data, and model interpretability. Recent Large Models (LMs), built upon Transformer architectures and self-supervised pre-training, offer a transformative new paradigm to overcome these long-standing bottlenecks. This review provides the first comprehensive survey of LM applications in BPHM, systematically examining how these models address challenges in the field. We begin by elucidating the foundational technologies enabling LMs, including Transformer architectures, self-supervised learning, large-scale multimodal datasets, and PEFT techniques. We then categorize recent progress along four critical dimensions: mitigating data scarcity, enhancing generalization and robustness, integrating domain knowledge for interpretability, and enabling system-level automation. Despite promising results, significant challenges remain across data accessibility, intelligence validation, trustworthiness, and deployment feasibility. To guide future research, we propose a roadmap focused on building collaborative data ecosystems, validating intelligence for industrial applications, enhancing trustworthiness with physics-informed designs, and enabling efficient on-device deployment. This review establishes a systematic approach to understand and advance LM-driven BPHM, providing researchers and practitioners with essential insights for developing next-generation battery management systems capable of safe, reliable, and autonomous operation throughout battery lifecycles.

---

### DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph

Authors: Zhihao Xiao, Mengting Li, Xintao Wang, Linfeng Li, Limin Shui, Mengqi Ji, Borui Cai
Published: 2026-05-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.05170v1

Role-playing agents (RPAs) have emerged as a key application of large language models, enabling immersive and high-fidelity character simulation. Accurate role-playing of established characters requires not only stylistic imitation but also temporally consistent and causally grounded behavioral reasoning. However, existing RPAs primarily rely on static character descriptions and unstructured memory, limiting their ability to maintain long-term narrative and personality coherence. We introduce DREAM, a structured memory framework for role-playing agents inspired by the Activating Event-Belief-Consequence (ABC) cognitive model. DREAM transforms unstructured literary text into an Event-aware Memory Graph (EMG) that organizes character experiences into temporally ordered and causally linked event graph. This representation enables the construction of dynamic, dual-granularity character profiles that capture both stable personality traits and event-driven behavioral evolution. We further propose the Temporal Causal Memory (TCM) benchmark to evaluate temporal consistency and long-range causal narrative coherence. DREAM achieves state-of-the-art performance across CoSER, LIFECHOICE, and TCM, outperforming multiple strong baselines. Our approach demonstrates the effectiveness of structured memory in enhancing the interpretability and consistency of role-playing agents.

---

### ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control

Authors: Jindong Li, Yang Yang, Zihao Liu, Yutao Yue, Menglin Yang
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.05169v2

Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumulate temporal, factual, character, commonsense, and stylistic errors as the story grows. We propose ConWriter, a training-free framework for consistency-aware long-form story generation. ConWriter writes stories incrementally at the scene level, guided by static story requirements, dynamic narrative memory, symbolic state reasoning, and uncertainty-aware risk signals. Rather than treating long-story generation as a single free-form decoding process, ConWriter maintains evolving story states, checks whether new scenes satisfy required narrative transitions, and uses uncertainty-aware risk signals to prioritize validation and localized repair. This enables consistency control during generation, before local errors propagate into later scenes. We evaluate ConWriter on ConStory-Bench across four long-story tasks, three target lengths, and multiple base LLMs following the official evaluation protocol. Across models and story lengths, ConWriter consistently matches or improves upon direct generation and outperforms the recent training-free baseline DOME in narrative consistency. These results demonstrate the effectiveness of lightweight neuro-symbolic consistency control for training-free long-form story generation. Code is available on \href{https://github.com/jindongli-Ai/ConWriter}{GitHub}.

---

### ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control

Authors: Jindong Li, Yang Yang, Zihao Liu, Yutao Yue, Menglin Yang
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.05169v1

Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumulate temporal, factual, character, commonsense, and stylistic errors as the story grows. We propose ConWriter, a training-free framework for consistency-aware long story generation. ConWriter writes stories incrementally at the scene level, guided by static story requirements, dynamic narrative memory, symbolic state reasoning, and uncertainty-aware risk signals. Rather than treating long-story generation as a single free-form decoding process, ConWriter maintains evolving story states, checks whether new scenes satisfy required narrative transitions, and uses uncertainty-aware risk signals to prioritize validation and localized repair. This enables consistency control during generation, before local errors propagate into later scenes. We evaluate ConWriter on ConStory-Bench, covering four long-story tasks: continuation, generation, expansion, and completion. Due to the high cost of long-form generation and evaluation, we use the first five cases from each task and test 3k, 6k, and 12k target lengths across Qwen3.5-Plus, DeepSeek-V4-Flash, and GPT-5 series. Experiments follow the official ConStory-Bench evaluation protocol.

---

### Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models

Authors: Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang
Published: 2026-05-27
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.05168v1

Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in intermediate steps rather than from global incompetence. We show that these bugs are frequently repairable: inserting a short patch generated by a weak probe model after the same strong-model reasoning prefix can redirect the trajectory toward a correct solution. However, this corrective effect is not reliably internalized by directly fine-tuning on weak patches or repaired trajectories, suggesting that the useful signal lies not in the intervention text itself, but in how it reshapes the model's future reasoning distribution. We therefore propose Woodpecker Distillation, a weak-to-strong training framework that learns from contrastive local interventions. Our method contrasts successful and unsuccessful weak-model patches at the same prefix, constructs a corrective teacher distribution from their induced future token predictions, and distills this signal into the strong model. Experiments on mathematical reasoning benchmarks show that Woodpecker Distillation consistently improves strong-model performance and outperforms direct imitation baselines.

---

### CNM-BERT: A Drop-In Structural Embedding for Chinese Characters via Ideographic Description Sequences

Authors: Thomas Sing-wing Wu, Liqian Yan
Published: 2026-05-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.05167v1

Token-based encoders like BERT treat Chinese characters as atomic identifiers, ignoring their recursive orthographic structure. Consequently, models rely on contextual co-occurrence, degrading performance on rare and out-of-vocabulary (OOV) characters. We propose the Compositional Network Model (CNM), a lightweight augmentation that injects discrete compositional structure into Transformer encoders. CNM parses Ideographic Description Sequences (IDS) into trees, encodes them via a recursive Tree-MLP, and fuses the structural embeddings into BERT without modifying the backbone. Evaluated on the Wu et al. (2025) structural-probing benchmark, CNM-BERT outperforms the strongest baseline (ChineseBERT) on long-tail and OOV characters by +9.8 Structure accuracy and +7.7 Radical F1. Furthermore, CNM-BERT achieves consistent gains across CLUE, MRC, and NER tasks at both base and large scales, demonstrating that explicit structural injection delivers both robust OOV understanding and tangible downstream value.

---

### To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussions

Authors: Dimitris Tsirmpas, Katerina Korre, John Pavlopoulos
Published: 2026-05-27
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2607.28643v1

Automating facilitation in online discussions is a long-standing social concern given the increasing time we spend on online spaces and the failure of content moderation approaches. While studies have been conducted on how to facilitate, none have answered the essential question of when to do so. A potential answer is using LLMs, which ostensibly make automated, large-scale intervention increasingly feasible. In this study, we examine when LLMs decide to facilitate by defining what facilitation is, observing when humans decide to facilitate, and comparing their decisions with those made by LLMs. To this end, we create PEFK, a corpus standardizing and aggregating all relevant facilitation datasets. We are the first to run a survey on facilitation timing, which we execute using expert facilitative participants and LLM-as-a-judge models. We discover that while humans are more cautious, LLMs are excessively eager to facilitate, although both are more certain when judging that facilitation is not needed. We then investigate whether this behavior can be corrected using alternative setups for LLMs and training ModernBert classifiers on established datasets, finding that the latter perform more reliably than the former, although current datasets impose a relatively low performance ceiling.

---

### Semi-Supervised Text-Attributed Graph Distillation

Authors: Yurui Lai, Samir Moustafa, Renchi Yang, Tsz Nam Chan
Published: 2026-05-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.20477v1

{\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics. Existing representation learning methods over TAGs suffer from severe scalability bottlenecks, particularly together with {\em Large Language Models} (LLMs). While data distillation offers a promising data-centric solution, existing methods fail to capture the complex interplay between graph and text modalities, struggle with the label scarcity inherent in semi-supervised settings, and lack the ability to produce the human-readable textual attributes required for downstream LLM-based tasks. To address these challenges, we propose \algo{}, a unified semi-supervised framework guided by the {\em Wasserstein Distance} (WSD). Grounded in our empirical findings on real TAGs, \algo{} introduces a graph-text collaborative encoding module that utilizes dual-pathway encoders (graph-aware and -free) within a collaborative self-training scheme to harvest reliable pseudo-labels and fuse complementary graph-text features. Furthermore, we develop a theoretically grounded WSD-based graph sketching algorithm and a cost-effective LLM text synthesis module, which leverages cluster-based keyword extraction to generate coherent, human-readable summaries for condensed nodes. Extensive experiments on benchmark datasets demonstrate that \algo{} achieves a state-of-the-art performance-compression trade-off in terms of both GNN- and LLM-based downstream tasks, enabling effective and efficient TAG learning or analytics.

---

### DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents

Authors: Jiamian Wang, Ruiyi Zhang, Tong Yu, Jing Shi, Samyadeep Basu, Rajiv Jain, Zhiqiang Tao, Tong Sun
Published: 2026-05-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.26122v1

Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training environment, and whose properties directly shape what search strategies and generalization abilities the agent can develop. While prior works have made encouraging progress in improving training data quality, existing environments remain predominantly text-based and existing approaches can struggle to construct training environments that are controllable, scalable, and account for multimodal data. Given this, we propose DocArena, a fully automated data curation pipeline building on the practical need for multimodal document search and question-answering. It transforms raw document collections into training environments for search agents without any human annotation. The pipeline first structures and indexes documents through MLLM-based visual perception, then profiles and leverage the cross-page information distribution to construct reasoning-intensive QA pairs, as well as performs cascaded quality assurance operations via MLLM. We introduce DocArena-79K with QA pairs from 8,336 documents spanning 16 domains and 49 languages. We further design a Doc-Search agent infrastructure that decouples visual perception from the policy model, allowing text-based LLMs to serve as the reasoning backbone for multimodal document retrieval and QA. Under a unified evaluation framework where only the policy model differs, experiments on six multimodal document scenarios and seven text-based QA benchmarks show that agents trained on DocArena data achieve the best performance on both retrieval accuracy and QA quality. Further analysis on agent search behaviors confirms the effectiveness and controllability of the constructed training environment.

---

### Dot-Flik: A Scalable Edge AI Architecture for Distributed Insect Monitoring

Authors: Mattia Consani, Denisa-Andreea Constantinescu, Åse Håtveit, Titus Venverloo, Fabio Duarte, Carlo Ratti, David Atienza
Published: 2026-05-27
Categories: cs.NI, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.26121v1

Global insect population declines necessitate scalable, continuous monitoring systems, yet existing vision-based solutions remain constrained by high hardware costs, energy demands, and reliance on centralized processing or cloud connectivity. This article presents three contributions to address these limitations. First, we propose a motion-informed frame filtering algorithm based on temporal differencing, gamma-corrected motion amplification, and block-based motion density analysis that discards irrelevant frames at the edge while preserving insect activity, without requiring deep learning inference on the sensing device. Second, we introduce a distributed, hierarchical IoT architecture that decouples data acquisition from AI classification through this edge-level preprocessing, projecting fractional scaling of central processing requirements and significantly increasing monitoring coverage compared to monolithic single-stream approaches. Third, we validate the complete system through real-world outdoor deployments on low-cost commodity hardware along four axes: real-time performance, network scalability, hardware cost, and energy efficiency under varying wind conditions. Results demonstrate 60-80% frame reduction under light-wind conditions, sustained real-time 30 FPS operation with 12.8 ms of computational headroom, up to 22.6% energy savings, and support for 5-6 concurrent edge streams per central node. These findings establish a practical foundation for dense, low-cost biodiversity monitoring networks in urban environments.

---