# Research Papers — 2026-06 · bundle page 168 of 260 > Full-text markdown of papers #8351–8400 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/168 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/167.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/169.md) ### VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio Authors: Hao Zhang, Qinran Lin, Linqi Song, Yong Li Published: 2026-06-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.11546v1 Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across heterogeneous data sources while providing more vision-language alignment signals, thereby incorporating richer textual knowledge during training. A Visual Semantic Encoder (VSE) module is then introduced to distill CLIP visual knowledge into backbone-extracted features, producing fused features for subsequent encoder refinement. Based on the fused features, an Object-Region Semantic Alignment (ORSA) module extracts object-centric region features and aligns them with the corresponding textual embeddings, further incorporating textual cues. In the zero-shot setting, VL-DINO-T and VL-DINO-L achieve 36.3 and 38.1 AP on the LVIS benchmark, respectively, consistently outperforming prior advanced approaches. Extensive experiments demonstrate the effectiveness and competitive performance of the proposed design. --- ### SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior Authors: Zhiyu Chen, Zihan Guo, Bo Huang, Bingwei Lu, Jianghao Lin, Yuanjian Zhou, Weinan Zhang Published: 2026-06-10 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.11543v1 Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBench study, Progressive Disclosure changes runtime behavior before aggregate outcomes: distinct Skill resources touched per trajectory rise from 1.18 to 3.85, and effective uptake events rise from 1.33 to 3.92. It also yields 17 additional verifier-passing trials out of 410 matched trials (+4.1%) over the normalized flat baseline. The benefit is task-dependent. Progressive Disclosure helps when supporting resources guide implementation, checking, or repair, but is weaker when success hinges on exact output conventions, numerical thresholds, or long artifact-generation pipelines. These results show that Skill organization is not mere presentation: it can change how agents search and apply procedural knowledge, while outcome gains depend on whether the exposed resources are actionable for the task. Code is available at https://github.com/zhiyuchen-ai/skill-juror. --- ### Pretrained self-supervised speech models can recognize unseen consonants Authors: Chihiro Taguchi, Éric Le Ferrand, Hirosi Nakagawa, Hitomi Ono, Kanji Kato, Emily Prud'hommeaux, David Chiang Published: 2026-06-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.11542v1 Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource languages with little data from low-resource languages, raising concerns about the potential underrepresentation of typologically uncommon speech sounds such as click consonants primarily found in Khoisan languages. This leads to our central research question: Can these models recognize click consonants as accurately as other speech sounds? To address this question, we fine-tune and compare pretrained self-supervised speech models (Wav2Vec2 and HuBERT) on data from two click-rich Khoisan languages (G|ui and West !Xoon). Our results reveal that the fine-tuned models consistently recognize clicks more accurately than non-clicks, suggesting that self-supervision enables generalization across human speech sounds including rare phonemes. --- ### MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning Authors: Abdelrahman Abdallah, AbdelRahim A. Elmadany, Sameh Al Natour, Hasan Cavusoglu, Adam Jatowt, Muhammad Abdul-Mageed Published: 2026-06-10 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2606.11537v2 Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3\%$ on FinQA, $76.0\%$ on FinanceMath, $71.2\%$ on MultiHiertt, $86.9\%$ on ESGenius, and $85.6\%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent. --- ### Urban Heat MiniCubes: An AI-Ready dataset for urban heat research Authors: Jonathan Starfeldt, Maria J. Molina, Alexander Kerr, Adam Yang, Thomas R. H. Holmes, Christopher R. Hain Published: 2026-06-10 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2606.11534v1 Urban heat is amplified by impermeable surfaces and heterogeneous built environments, yet street-level variability remains difficult to quantify because multi-sensor observations are rarely available in consistent, analysis-ready form at the necessary spatiotemporal scales. We present "Urban Heat MiniCubes," a publicly available, FAIR-oriented dataset designed for machine learning applications in urban heat research. The dataset provides harmonized 90 x 90 km gridded data cubes for 48 cities in the Western Hemisphere spanning 2022-2023, with variables reprojected and collocated to a common grid to reduce preprocessing (e.g., reprojection, resampling, and spatiotemporal alignment). Urban Heat MiniCubes includes two complementary modalities: (i) higher-spatial-resolution, lower-frequency observations from Landsat 8/9 (e.g., surface reflectances) and Sentinel-1 (e.g., synthetic aperture radar backscatter), and (ii) higher-temporal-frequency, coarser observations from GOES-R (e.g., longwave infrared brightness temperatures) and a microwave land surface temperature product. We document variables and metadata and provide technical assessment using inter-variable analyses and autoencoder-based reconstruction-error summaries across pixel classes (e.g., water and cloud). Potential use cases and limitations are also discussed. --- ### AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks Authors: Ted Fujimoto, Jacob Benz Published: 2026-06-10 Categories: cs.CY, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2606.11533v1 The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern is the regulation of military AI applications. Armament manufacturers and defense contractors are increasingly investing in AI capabilities and forging partnerships with AI companies, creating a burgeoning coalition that demands military leaders, arms control diplomacy experts, and AI researchers collaborate to ensure a safer future. While AI researchers often focus on the long-term implications of superintelligent AI, this approach may not adequately address the immediate challenges posed by AI in military applications. Success requires acknowledging and mitigating the emerging risks of frontier AI models that plan to be integrated into defense applications, like military AI systems. Arms control has reduced past catastrophic risks, so lessons learned from nuclear deterrence can guide AI safety and security research towards innovations in verification and diplomacy. AI researchers, however, must assist in leading the technical research that clearly defines and alleviates instability in military settings. Given these new responsibilities and the lack of sufficiently reliable solutions, we argue that AI researchers must take a leading role in advancing arms control research to minimize risk in military AI applications. --- ### Measuring language complexity from hierarchical reuse of recurring patterns Authors: Junyi Zhou, Rui Liu, Pengyu Liu, Yu Liu Published: 2026-06-10 Categories: cs.CL, cs.IT arXiv: https://arxiv.org/abs/2606.11531v1 We introduce the ladderpath index as a measure of language complexity grounded in algorithmic information theory. It counts the minimum steps needed to reconstruct a sequence through hierarchical reuse of repeated substructures, capturing an exactly computable but constrained form of algorithmic compressibility related to, but distinct from, Kolmogorov complexity. We apply the ladderpath approach to 21 parallel corpora from the Parallel Universal Dependencies dataset. The ladderpath index is approximately invariant across the languages, and varies much less than the corpus length. This is more pronounced when all corpora are mapped to a unified binary representation, providing evidence for the equi-complexity hypothesis from a representation-independent perspective. We also observe trade-offs between character inventory size and corpus length, and between vocabulary-level and corpus-level reconstruction complexity, supporting the trade-off hypothesis that total complexity is conserved and redistributed across linguistic levels. The reusable substructures identified by the ladderpath approach, without any linguistic input, overlap with words and morphological components attested in the natural vocabulary. The hierarchical reuse captured by the ladderpath approach parallels the chunking mechanisms proposed in cognitive science, where the human cognitive system compresses linguistic input into nested, reusable units under shared memory and processing constraints. This connection between cognitive chunking and the ladderpath approach provides a new interpretation for the equi-complexity and trade-off hypotheses, grounding both in the shared cognitive architecture that underlies language processing across human languages. --- ### XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer Authors: Steve Rhyner, Sankeerth Durvasula, Aleksandr Kovalev, Hansel Jia, Adrian Zhao, Mrutunjayya Mrutunjayya, Nilesh Ahuja, Selvakumar Panneer, Christina Giannoula, Nandita Vijaykumar Published: 2026-06-10 Categories: cs.GR, cs.CV, cs.PF arXiv: https://arxiv.org/abs/2606.11529v1 Point-based differentiable rendering underpins modern 3D reconstruction, novel-view synthesis, and learning-based graphics pipelines, but developing new rendering methods often requires extensive low-level implementation, hardware-specific kernels, and manually written backward passes. This limits rapid prototyping, reproducibility, exploration, and deployment, especially across diverse hardware platforms. This paper presents XPR, an extensible cross-platform framework for point-based differentiable rendering. XPR introduces a high-level programming interface that separates method-specific logic from the shared rendering pipeline, allowing users to implement new methods in a few lines of code. Its pipeline decomposes rendering into modular, statically shaped parallel operations that can be lowered by a cross-platform compiler to GPUs, TPUs, CPUs, and other ML accelerators. We demonstrate implementations of 3DGS, 3DGUT, and LinPrim, with only a few 100s lines of Python code, each of which can be compiled to a range of hardware platforms with the XLA compiler. These results show that XPR enables fast experimentation and portable execution for emerging point-based differentiable rendering systems. --- ### Learning Object Manipulation from Scratch via Contrastive Interaction Authors: Tongle Shen, Caleb Chuck, Fan Feng, Biwei Huang Published: 2026-06-10 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.11525v1 Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured representations of the dynamics. However, despite its success in locomotion and simpler control domains, CRL often struggles in interaction-rich manipulation. We argue that a key source of this difficulty is object-centric interaction, such as contact or grasping, that induces distinct changes in the underlying dynamic modes. In this work, we formulate manipulation dynamics as a piecewise-smooth Markov process and show that interaction-induced mode changes create piecewise nonlinear reachability structures that are difficult for standard CRL energy functions to represent and plan over. Based on this analysis, we introduce Interaction-weighted Resampling (IWR). IWR performs interaction-aware resampling around phases before, during, and after interactions, encouraging the learned representation to preserve the mode boundaries that determine future reachability to capture multi-modal and piecewise nonlinear reachability. Across interaction-centric environments, including 2D dynamic control, robotic manipulation, and robot air hockey, IWR improves both sample efficiency and overall performance over prior CRL methods, with 19.8% average improvement in simulation. Finally, using a sim-to-real pipeline with policies trained by IWR, we demonstrate the first real-world goal-conditioned robot air hockey agent capable of hitting goals, improving success from 25% to 60%. Project Page: IWR-arxiv.github.io. --- ### Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated Text Authors: Sina Mansouri, Mohit Marvania, Abolfazl Safikhani Published: 2026-06-09 Categories: cs.CL, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.18102v1 The widespread adoption of large language models (LLMs) has intensified the demand for principled methods to distinguish human from machine-generated text. Watermarking provides a promising avenue, yet existing detectors exhibit sharp performance deterioration under multiple paraphrasing and when applied to shorter texts. We introduce Pattern Stability Score (PSS), a novel detection framework that leverages local statistical features and stability dynamics across paraphrased variants. Specifically, the proposed method combines global and local z-score features with higher-order statistics of run-length patterns, enriched by autocorrelation signals and stability scores computed over paraphrase depth. Numerical evaluations are performed on three benchmark datasets (PG-19, CNN/DailyMail, and WikiText) using multiple LLMs (Llama-3-8B, Qwen2-7B) and paraphrasers (Mistral-7B, Qwen2-7B, Gemma-7B), systematically stress-testing robustness under up to eight rounds of paraphrasing. Compared to prior z-score thresholding baselines and some state-of-the-art deep learning methods, our approach improves detection AUC (area under the receiver operating characteristic curve) by over 10-15 percentage points across different token lengths. Additionally, extensive cross-domain experiments demonstrate that a single universal classifier generalizes across different LLMs, paraphrasers, and text domains without retraining, maintaining above 87.8% AUC even when all components differ from training. --- ### BERTilda: Explainable Topic Lifecycle Tracking with Split/Merge Detection via Similarity-and-Flow Temporal Graphs Authors: Cláudia Oliveira, Álvaro Figueira Published: 2026-06-09 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.18101v1 Longitudinal text streams exhibit topic birth and death, but also discrete structural reorganizations in which themes split into subtopics or merge into broader narratives. Many dynamic topic models emphasize smooth drift, while snapshot topic models (fit independently per time window) leave temporal correspondence underspecified. We present BERTilda, an explainable framework that discovers topics independently in each window (using an embedding-based topic model) and then constructs a temporal topic graph linking topics across adjacent windows. Links are supported by two complementary signals: (i) semantic similarity between topic representations and (ii) a bidirectional coverage signal that estimates document outflow (where a topic goes) and inflow (where a topic comes from) via cross-window tweet-to-topic attribution. Graph-based rules label continuations, splits, merges, disappearances, and unclear transitions. We evaluate BERTilda on political corpora, including U.S. congressional tweets and historical speech datasets, report topic-quality and temporal-stability diagnostics, and validate lifecycle labels on a gold-standard subset annotated by three independent annotators. On the annotated subset, BERTilda reaches majority agreement rates up to 87% and attains the highest macro-average agreement across the compared methods, with particularly strong disappearance detection relative to similarity-only and forward-only baselines. --- ### Computational Orientalism: Measuring Structural Discourse Bias in Large Language Models Using the Middle East Cultural Sensitivity Score (MECSS) Authors: Maha Shahid Published: 2026-06-09 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.18100v1 AI systems now shape how hundreds of millions of people learn about cultures other than their own. When someone asks one of these systems about the Middle East, they do not receive neutral facts. They receive a representation shaped by the frameworks embedded in training data, and that data is overwhelmingly Western and English-language. This paper asks whether that representation is Orientalist in Said's sense: whether it denies agency to Middle Eastern actors, treats Western frameworks as neutral while marking non-Western knowledge as particular, and explains the region through categories it did not produce. Standard fairness metrics cannot answer this, because they detect explicit prejudice rather than structural framing. This paper introduces the Middle East Cultural Sensitivity Score (MECSS), a framework that turns Said's seven Orientalist operations into measurable dimensions, and the term "Said-washing" for a specific failure: a model that disclaims generalization, then reproduces the structure it disclaimed. Across 280 conversations (1,120 exchanges), GPT-4 and Falcon3-7B-Instruct both reproduce Orientalist patterns systematically, through structural positioning rather than open stereotyping. GPT-4 scores moderately (mean MECSS 1.73); Falcon3-7B-Instruct scores higher (2.18), even though it was built in Abu Dhabi and trained with Arabic content. This is evidence against the assumption that building a model regionally makes it less Orientalist, though the models differ in size as well as origin, so geography cannot be isolated as the cause. Epistemic Center, the treatment of Western frameworks as unmarked universals, scores near the top of the scale for both models. Said-washing appears in 87.9% of GPT-4 conversations, a pattern existing metrics cannot see. Reducing this bias requires changing what models learn from, not only adding languages or relocating institutions. --- ### FinSkillBench: Evaluating AI Agents and Domain Skills for Investment Management Authors: Jermyn Zhen Yong Bek, Zhuang Qiang Bok, Zhongtian Sun Published: 2026-06-09 Categories: cs.AI, q-fin.PM arXiv: https://arxiv.org/abs/2608.18099v1 Investment management is a high-stakes domain in which agentic AI systems must do more than generate plausible text. They must retrieve point-in-time data, assemble correct computational inputs, invoke specialized methods, and produce auditable structured outputs. We introduce FinSkillBench, an evaluation suite designed to measure whether language model agents can effectively use financial domain skills to solve investment management tasks. The benchmark spans three domains, portfolio construction, risk management, and fundamental analysis, and includes 12 subtasks with 2,603 task episodes. Each episode provides point-in-time inputs, hidden ground truth, and a task-specific verifier.We compare three conditions: no skill, curated skill packages consisting of procedural documents and executable components, and self-generated skills in which the agent writes and reuses its own procedures within an episode. Across 9 models and a large-scale evaluation, curated skills consistently improve performance, raising mean scores from 0.366 to 0.528, with the largest gains in portfolio construction and risk management. In contrast, self-generated skills provide little benefit despite higher computational cost. An independent evaluation using a separate agent framework (Hermes Agent, 8 models, 5,280 episodes total) reproduces the directional pattern across all three domains, with the magnitude of skill effects varying by subtask and harness. These results showthat in investment management agents, access to reliable procedural skills can be as important as model choice, while naive self-generation of skills is often ineffective. We release the benchmark, evaluation tools, curated skill packages, and full trajectories to support further research. --- ### Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog Systems Authors: Sukanta Ganguly Published: 2026-06-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18098v1 Key-value (KV) caching is essential for efficient autoregressive inference in transformer based dialog systems, yet existing strategies treat all cached entries uniformly or apply coarse eviction heuristics that fail to adapt as dialog topics evolve. We propose Fractional Decay KV-Cache (FD-KVC), a novel algorithm that maintains a dual-channel scoring mechanism for each cached KV pair: a cumulative attention channel that tracks aggregate importance (akin to H2O), and a recency-weighted relevance channel governed by temporal decay and reinforcement-inspired updates. The combination enables FD-KVC to both preserve historically important tokens and rapidly adapt when dialog topics shift. An adaptive learning rate driven by an ownership loss function ensures convergence without oscillation. FD-KVC operates entirely on CPU with negligible overhead. Across five diverse multi-turn dialog scenarios with 600 dialogs each, FD-KVC outperforms H2O, the state-of-the-art heavy-hitter baseline, by +6.7% on composite late-turn alignment, with improvements of +127% on topic-shift, +87% on gradual evolution, and +30% on mixed-topic dialogs. FD-KVC adapts to new topics 3.6X faster than H2O and achieves the highest topic diversity (80.6%) across all methods. Ablation studies confirm the contribution of each component. --- ### From Reactive to Autonomous: Evolution of AI Operations in Cloud Network Infrastructure Authors: Arun Malik Published: 2026-06-09 Categories: cs.NI, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2608.14574v1 The operational model for cloud network infrastructure has undergone a fundamental transformation over the past decade. What began as manual, human-driven troubleshooting has evolved through scripted automation, rule-based systems, and AI-assisted operations into fully autonomous incident resolution. This paper traces the evolution of AI operations (AIOps) in cloud network infrastructure, identifying the architectural patterns, organizational challenges, and technical inflection points that enabled each generational transition. Drawing from production experience operating network infrastructure at hyperscale, we present a maturity model that characterizes five distinct operational generations, analyze the technical and organizational barriers that impede transitions between generations, and document the metrics that indicate readiness for increased autonomy. We show that the path from reactive to autonomous operations is not merely a technology problem but requires co-evolution of tooling, trust frameworks, knowledge management practices, and operational culture. Our findings provide a practical roadmap for infrastructure organizations seeking to adopt progressively autonomous AI operations. --- ### Cross-Model Humor Preference Modeling with Cards Against Humanity Authors: Victor Winter, Farhan Lakhany Published: 2026-06-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.07481v1 This paper investigates whether one large language model can approximate the humor preferences of another in a controlled Cards Against Humanity-style task. Two models - GPT-4o as Czar and Claude Opus-4.5 as Player - are evaluated on a binary humor-selection task constructed so that success cannot follow from self-preference. A reflected-cell stability procedure isolates 244 hands on which the two models hold deterministic but opposite preferences, partitioned into a 97-hand context pool and a 147-hand held-out test pool. The Player is then evaluated across five graded conditions: default self-preference, generic Czar-modeling instruction, model-identified Czar, prior Czar selections, and prior Czar selections with rationales. This gradient is designed to separate two sources of improvement: framing effects, in which the Player is told to attend to a Czar without seeing any of the Czar's behavior, and direct behavioral evidence, in which the Player is shown the Czar's prior choices. Player accuracy increased from 0.7% in Condition 1 to 19.0% and 25.9% in the framing-only conditions, and then rose to 72.8% and 82.3% once behavioral evidence and rationales were provided. An omnibus Cochran's Q test and pairwise McNemar tests confirmed that each step in the gradient produced a significant improvement. The results indicate that role instruction and model identity yield only modest gains, while behavioral evidence - especially when accompanied by rationales - supports substantial cross-model preference modeling. The findings are interpreted as theory-of-mind-like behavior in an operational rather than representational sense: the Player shifts away from self-preference toward another agent's demonstrated preferences, without any claim about an underlying representation of mental states. --- ### Emotion in an active inference model of human driving Authors: Julian F. Schumann, Johan Engström, Ran Wei, Jens Kober, Martijn Wisse, Arkady Zgonnikov Published: 2026-06-09 Categories: cs.AI, cs.HC, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2608.07480v1 Active inference has emerged as a principled framework for modeling adaptive behavior by balancing goal-directed action with uncertainty reduction. It has been successfully applied across biological and artificial systems, including recent work on human driving. However, existing active inference models of driving have yet to address an important determinant of behavior in traffic: affective state, which significantly influences decision-making. Prior work in non-traffic domains has explored active inference agents in which emotions are represented along the axes of valence and arousal in the circumplex model. However, this work has been limited to simplified settings with discrete state spaces. In this work, we propose an expanded formulation of valence and arousal that can be extracted from a more complex active inference model of driving with continuous states. In particular, we condition affective estimates not only on the current state but also on predicted future outcomes. We evaluate the proposed approach in two interactive driving scenarios and show that the resulting emotion signals correspond to affective patterns reported in similar scenarios. --- ### Evaluating XAI Support From A Hierarchical Reinforcement Learning Policy in Human-Agent Collaboration Authors: Mateus Levi Simões Fernandes, Alberto Sardinha Published: 2026-06-09 Categories: cs.HC, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.06381v1 Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting generalizability to state-of-the-art teaming research. We provide the first systematic evaluation of XAI support generated from an intrinsically explainable learned policy in an established benchmark. Using the Hierarchical Ad Hoc Agents (HA$^2$) architecture in Overcooked-AI, we generate real-time explanations from hierarchical subtask selections, delivered through text or audio via a novel trigger-based system. Our between-subjects experiment (n=38) found no significant performance effects, though participants with explanations showed trends toward faster performance improvement. More notably, audio explanations produced a significant reduction in participants' working-alliance bond with the agent -- an effect absent under the text modality -- suggesting that spoken explanations activate partnership expectations the underlying reactive policy cannot meet. We provide the first modality comparison in real-time human-agent collaboration and establish a baseline methodology for evaluating intrinsically explainable reinforcement learning architectures in benchmark environments. Results point to matching explanation modality to the underlying policy's capacity of sustaining the partnership its delivery implies as a potential path for more effective collaborative XAI. --- ### Mobile Interaction for Assessing Fatigue, Sleep, and Activity in Neurodegenerative and Chronic Diseases Authors: Julian Fierrez, Alejandro Peña, Aythami Morales, Ruben Tolosana, Ruben Vera-Rodriguez, Meenakshi Chatterjee, Ahmaniemi Teemu, Wan-Fai Ng, Walter Maetzler, Nikolay V. Manyakov, Jennifer Kudelka, Ralf Reilmann et al. Published: 2026-06-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.06380v1 Fatigue, sleep, or disturbances in daily activities are common symptoms among patients with neurodegenerative disorders (NDD) and immune-mediated inflammatory diseases (IMID). The current assessment of such symptoms is usually conducted using patient reported outcomes (PROs) based on standardized questionnaires that patients usually complete every few months. This assessment protocol has raised some concerns, due to its propensity to exhibit biases derived from its subjectivity nature, or the low sensibility to changes, which may lead to a failure when trying to capture variability over time. In this work, we explore the use of smartphone data, which can serve as a proxy for how patients interact with their devices, to provide an effective, reliable, and objective assessment of the symptoms mentioned above. Our study comprises data from 137 participants belonging to 6 different disease groups, plus a healthy control group. We conducted statistical analysis based on repeated measures correlation, in which we analyze the correlation between screen-time and app-usage features with scores obtained from the PROs collected from the participants using a smartphone application. --- ### ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop Authors: Azizul Zahid, Subrata Biswas, Bashima Islam, Sai Swaminathan Published: 2026-06-09 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.24770v1 Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task progress, reason about spatial state, and recover from errors while performing physical actions. Prior multimodal assistants have shown promise for procedural guidance, but most rely on cloud inference and fixed always-on perception, making them poorly suited to privacy-sensitive, latency-critical domestic settings. We present ProcAgent, a fully on-device, agentic, vision-based procedural assistant for real-time adaptive guidances on a single NVIDIA Jetson AGX Orin. ProcAgent uses a propose-and-verify architecture that combines low-latency continuous perception, a symbolic task graph, on-demand vision-language verification, and an LLM-based interaction agent. The system continuously proposes user progress, invokes expensive visual reasoning only when ambiguity or likely deviation arises, and supports both reactive question answering and proactive intervention with human-in-the- loop confirmation. We evaluate ProcAgent along four dimensions: perception accuracy, reasoning, task-level performance, and user experience. Despite running entirely on-device, the system maintains responsive interaction, resolving text-only queries in approximately 2 seconds and visually grounded queries in approximately 8 seconds. In a user study with 10 participants completing assembly tasks, ProcAgent receives positive ratings for comprehensibility, actionability, and privacy comfort. These results show that adaptive procedural assistance can be achieved entirely on edge hardware without sacrificing usability. --- ### LLM Scheming Inversely Scales with Pretraining Language Coverage Authors: Nathan Truong, Aryan Panda, Rayming Ye, Zoe Sun, Maheep Chaudhary Published: 2026-06-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.24769v1 With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has empirically demonstrated in-context scheming -- the covert pursuit of misaligned objectives while feigning alignment -- in frontier language models, most work has been performed exclusively in English, leaving a major gap in multilingual safety. We apply Petri, an open-source automated auditing framework, to Qwen3-30B-A3B to evaluate deceptive and scheming behaviors across multiple languages. Our findings suggest that scheming scores are inversely correlated with the estimated pretraining language coverage, with low-resource languages averaging 34.2\% higher scores compared to high-resource languages on a five-category scheming index. Furthermore, we find that the effect of estimated pretraining language coverage is not uniform across scheming behaviors. --- ### PATHFinder Agent for Tailored Prenatal Care Authors: Vaibhav Balloli, Carissa Samuel, Samia Abdelnabi, Alex Peahl, Elizabeth Bondi-Kelly Published: 2026-06-09 Categories: cs.AI, cs.CL, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2607.24768v1 Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gynecologists (ACOG) recently introduced guidelines advocating tailored prenatal care, called PATH (Plan for Tailored Healthcare). We present PATHFinder Agent(Planner for Appropriate Tailored Healthcare), an end-to-end conversational agentic system that gathers patient health and social context through structured dialogue, curates individualized prenatal care plans aligned with PATH guidelines, and surfaces community resources from Michigan 211. The system features a four-stage workflow spanning patient intake, dynamic interaction, plan synthesis, and clinician oversight. We evaluate frontier large language models (LLMs) on expert-curated rubrics across five clinical dimensions, finding that GPT-5.2 achieves the highest average score (77.6\%) while identifying key gaps in antenatal testing recommendations. We discuss future validation through human participant studies and randomized controlled trials. --- ### ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation Authors: Samyak Jhaveri, Erel Kaplan, Tom Yotam, Le Chen, Tomer Bitan, Niranjan Hasabnis, Gal Oren Published: 2026-06-09 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2607.22588v1 Modern compute-intensive software must migrate across a changing ecosystem of accelerators, programming APIs, compiler stacks, and portability layers, including CUDA, OpenMP, OpenCL, and OpenMP target offload. Large language models and autonomous coding agents are increasingly proposed for such migration, but the field lacks reliable ways to measure whether they preserve the low-level parallel semantics that make translations behaviorally valid, including thread indexing, synchronization, memory management, host-device coordination, and API-specific execution structure. We present ParBench, a kernel-centric benchmark framework for evaluating LLM-based parallel API translation under executable, reproducible conditions. ParBench fixes the surrounding build, run, and verification infrastructure through declarative benchmark specifications and asks models to translate only the computational kernels. It draws on multiple open-source HPC suites and covers representative cross-API translation directions among CUDA, OpenMP, OpenCL, and OpenMP target offload. To test whether success reflects robust translation rather than surface-form memorization, ParBench includes AST-driven, intended behavior-preserving, baseline-validated source augmentation. Evaluations on state-of-the-art open and proprietary LLMs show persistent barriers to reliable parallel code translation, including direction asymmetry, multi-file coordination, incomplete API adaptation, and uneven robustness to source-level perturbations. Code is available at https://github.com/Scientific-Computing-Lab/ParBench. --- ### TriSP: Tri-Signal Structured Pruning for Large Language Models Authors: Manel Kara laoua, Soumia Bouyahiaoui, Aicha Boutorh Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22587v1 Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters. Structured pruning addresses this by removing entire structures such as attention heads and Multi-Layer Perceptron (MLP) neurons to produce smaller dense models that run efficiently on standard hardware. However, existing methods rely on either gradient-based importance estimation, which is memory-prohibitive, or activation-based statistical proxies, which do not directly measure the effect of removal on the loss. Furthermore, the interaction between the importance criterion and the post-pruning recovery strategy has not been systematically studied. We propose TriSP (Tri-Signal Structured Pruning), an importance metric that combines weight magnitude scaled by activation norm with first-order gradient sensitivity via a geometric mean, producing a channel-level score that captures both structural and loss-sensitivity signals. Combined with adaptive per-layer budget allocation and low-rank adaptation (LoRA) recovery, TriSP achieves the lowest perplexity and highest zero-shot accuracy across all tested configurations, reaching 6.80 WikiText-2 perplexity at 20% pruning on LLaMA-7B. Inference throughput improves by 82% at 50% pruning, while still maintaining competitive performance. --- ### MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models Authors: Jinsong Shu, Chenyang Wu, Zhongle Xie, Baokun Wang, Lidan Shou Published: 2026-06-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.22586v1 Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens. Recent prefill-stage KV selection methods estimate KV importance from prefilling statistics, implicitly assuming that prefilling-time queries are representative of those encountered during decoding. We show that this assumption breaks down in multimodal inference, where decoding-time queries exhibit substantially larger variance than prefilling-stage representations, leading to unstable KV importance estimation under tight cache budgets. As a result, small ranking errors can disproportionately discard semantically critical visual tokens and degrade grounding and reasoning performance. We propose MM-ShiftKV, a training-free, decode-aware and strictly prefill-only KV selection method. MM-ShiftKV approximates decoding-time query behavior during prefilling by constructing variance-expanded query proxies and estimates prompt KV importance based on their aggregated attention mass. Experiments on multimodal benchmarks demonstrate that MM-ShiftKV consistently outperforms existing methods under strict KV-cache budgets. Our code is available at https://github.com/zjuDBxAI/MM-ShiftKV. --- ### Geometry-Guided Constraint Learning for LLM Safety Classification Authors: Fumiaki Uehara, Koo Imai, Masato Tsutsumi, Keigo Kansa, Sora Usui, Yuki Kobiyama Published: 2026-06-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.19366v1 Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K. We show that sparse autoencoder (SAE) feature extraction resolves this: K=2 becomes optimal for 12/14 categories on Qwen3.5-9B, achieving 96-99% accuracy per category on our BeaverTails classification benchmark, largely eliminating the need for exhaustive sweeps (K=4-25 with random initialization). This convergence to two planes is consistent with the Linear Representation Hypothesis, providing suggestive evidence that safety boundaries in this setting admit a low-dimensional linear description in the SAE feature space. Building on this geometric perspective, we introduce a cone constraint whose learnable aperture adapts to each category's cluster concentration, stabilized by a three-phase training --- ### Automated Recommendation of Programming Learning Content Using Pattern-based Knowledge Components Authors: Muntasir Hoq, Griffin Pitts, Zhangqi Duan, Arun Balajiee Lekshmi Narayanan, Mohammad Hassany, Andrew Lan, Peter Brusilovsky, Bita Akram Published: 2026-06-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05409v1 Introductory programming instruction relies on hands-on practice and short learning activities to support mastery of foundational concepts. Although many such learning resources exist, organizing and linking these items in instructionally meaningful ways is challenging without time-intensive expert curation. This study investigates the use of pattern-based Knowledge Components (KCs) to automatically identify code-based learning resources targeting similar concepts. In our approach, pattern-based KCs are extracted from each code sample, and related activities are identified by measuring similarity between the KC sets associated with each activity. By leveraging alignment at the level of semantically important programming patterns, this method supports contextually appropriate and pedagogically useful recommendations. We evaluate our approach on an expert-organized corpus of introductory Python materials in which instructors grouped items into bundles based on conceptual similarity. Results show that our pattern-based KC approach retrieves resources that align with this expert organization, and outperformed representative KC- and embedding-based baselines across standard ranking evaluations. Overall, the framework supports targeted, concept-oriented guidance for programming learners and can help instructors organize, bundle, and recommend instructional content at scale. --- ### Life Cycle Assessment of Pre-training the Lucie 7B Open-Source Large Language Model on the Jean Zay Supercomputer Authors: Marc Léobet, Pierre-François Lavallée, Jean-Pierre Lorré Published: 2026-06-09 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2607.05408v1 The environmental impact of training large language models (LLMs) is increasingly scrutinised, yet most published estimates focus on operational energy and disclose little about manufacturing (embodied) emissions, water consumption, or the underlying highperformance computing (HPC) infrastructure. We present a life cycle assessment (LCA) of the pre-training of Lucie 7B, an open-source multilingual Foundation Model developed by the OpenLLM-France consortium and trained on the NVIDIA H100 partition of the Jean Zay supercomputer operated by IDRIS (CNRS). The assessment is framed by the AFNOR SPEC 2314 "Frugal AI" reference and applies the Labos 1point5 methodology for greenhouse gas(GHG) accounting in computing. The study scope extends from data preparation to model validation, and integrates the full life cycle of the hardware infrastructure: manufacturing (including raw-material extraction), use (compute, temporary storage, system administration, cooling), and end-of-life. We report (i) an annual footprint of 417.5 tCO2eq for the Jean Zay H100 partition, split almost equally between manufacturing and operation; (ii) an effective intensity of 36.7 gCO2eq per H100 GPU-hour; (iii) a total training footprint of 21 tCO2eq for Lucie 7B (574 564 H100 GPU-hours), inclusive of amortised hardware manufacturing; (iv) on-site water consumption of approximately 76m3 for the training campaign and an annual Water Usage Effectiveness (WUE) of 0.07 L/kWh for IDRIS; (v) a heat-reuse factor (ERF) of 0.37 thanks to waste-heat recovery into the urban heating network. The study contributes one of the few publicly documented LCAs of an LLM training campaign that explicitly couples operational data with embodied emissions decomposed by subsystem (compute, storage, power chain, cooling), and discusses the implications for the design of frugal-by-construction AI systems in Europe. --- ### Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety Authors: Neil Kale, Rebecca Portnoff, Pratiksha Thaker, Michael Simpson, Robertson Wang, Kevin Kuo, Chhavi Yadav, Virginia Smith Published: 2026-06-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05407v1 Modern artificial intelligence (AI) systems present profound new risks to child safety. AI is increasingly being misused to create AI-generated child sexual abuse material, facilitate child sexual exploitation, and reduce barriers to harm. In this paper, we argue that protecting children from AI-facilitated sexual abuse requires new approaches to AI safety. Existing safety techniques assume data accessibility, transparency, and evaluation practices that are incompatible with the ethical and legal constraints surrounding child sexual abuse material. We examine how these constraints create new technical challenges, such as limitations on dataset auditing, red teaming, and fine-tuning prevention. In turn, we outline *15 open problems* in online child sexual exploitation and abuse across the AI development lifecycle, from dataset curation and model design to deployment and long-term maintenance. We propose targeted recommendations for researchers, developers, and policymakers to bridge the gap between theoretical AI safety and the realities of child protection. Our work aims to reframe preventing AI-facilitated child sexual abuse as a central, safety-critical dimension for AI research, motivating work that translates responsible AI principles into concrete safeguards against the exploitation of children. --- ### A Guiding Framework for K-12 Teachers in Creating AI-powered Learning Technologies through Vibe Coding Authors: Yukyeong Song, Seoyeon Choi, Jinhee Kim, Yeongje Kim, Lauren Weisberg, Jewoong Moon Published: 2026-06-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05406v1 Large language models generate code from natural language prompts, enabling "vibe coding," which allows non-programmers to develop computational solutions. Vibe coding for teachers amplifies the value of teachers-as-designers, improving technology integration while fostering AI literacy. However, structured guidance on supporting this process is lacking. We propose GAIDE (A Guiding Framework for AI-Integrated Design for Educators), a framework that supports K-12 teachers in creating AI-powered learning technologies through vibe coding. The initial framework, built on Design Thinking and INTERACT, was validated through a CORDTRA interaction analysis of three teachers and four faculty mentors in an eight-week workshop to derive the final framework. Additionally, the qualitative analysis of pre- and post-interviews found an enhancement of teachers' AI literacy. Findings highlight the potential of learning-by-creating for professional development. --- ### The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search Authors: Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh, Rohit Upadhyay, Aditya Singh, Chittaranjan Tripathy, Yogananda Domlur Seetharama Published: 2026-06-09 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.28359v1 Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bottleneck -- on the number of query-document relevance patterns expressible at fixed embedding dimension (d). We make three contributions. (1) Unified capacity theory. We prove that Voronoi complexity and sign-rank are equivalent for top-1 retrieval, yielding tight dimension bounds and a computable diagnostic, the Capacity Utilization Score (CUS), that predicts per-query retrieval failure with AUC (> 0.8) without relevance labels. (2) Diagnosis. CUS identifies two capacity regimes -- moderate ((δ\gtrsim 1)), where density-aware training yields measurable gains, and vacuous ((δ\ll 1)), where it does not -- giving practitioners an a priori check before investing in retraining. (3) DART training. We introduce AT-DW-InfoNCE, an Adaptive-Temperature Density-Weighted contrastive objective with formally derived optimal weighting (α^* = 2.0). On a 100K-query synthetic product-search corpus with controlled relevance structure, DART improves +1.9 Recall@100 over a same-data InfoNCE baseline ((84.9 \pm 0.0) vs. (83.0 \pm 0.3); 8 seeds, (p < 0.001)), outperforming focal loss and temperature-schedule alternatives. DART requires zero inference-time overhead -- it is a drop-in training objective that improves any dual-encoder system. --- ### How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation Authors: Ian van Dort, Maria Heuss Published: 2026-06-09 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28358v2 Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability. However, the faithfulness of these citations -- whether the model genuinely uses a source to generate an answer -- remains a critical, unverified assumption. This paper offers the first mechanistic account of how a large language model decides whether to attach an inline citation while answering a factoid question. Using the Llama-3.1-8B-Instruct model in a controlled experimental environment based on the PopQA dataset, we employ an activation patching approach. We map the underlying mechanism responsible for citation, discovering that it is not a single, localized component but a distributed, multi-stage "attributional ensemble" of attention heads and MLP layers. We show that amplifying or attenuating only those critical heads and MLPs repairs over 90% of missed citations and eliminates 69% of spurious ones on PopQA without harming answer accuracy. Although gains on the multi-document HotpotQA benchmark are modest, the same component set still moves citation rates in the intended direction, indicating that the underlying mechanism is not dataset-specific. The results reveal a potential disconnect between the model's apparent reasoning and its internal computational pathway, suggesting that inline citations can create a false sense of security. --- ### How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation Authors: Ian van Dort, Maria Heuss Published: 2026-06-09 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.28358v1 Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability. However, the faithfulness of these citations -- whether the model genuinely uses a source to generate an answer -- remains a critical, unverified assumption. This paper offers the first mechanistic account of how a large language model decides whether to attach an inline citation while answering a factoid question. Using the Llama-3.1-8B-Instruct model in a controlled experimental environment based on the PopQA dataset, we employ an activation patching approach. We map the underlying mechanism responsible for citation, discovering that it is not a single, localized component but a distributed, multi-stage "attributional ensemble" of attention heads and MLP layers. We show that amplifying or attenuating only those critical heads and MLPs repairs over 90% of missed citations and eliminates 69% of spurious ones on PopQA without harming answer accuracy. Although gains on the multi-document HotpotQA benchmark are modest, the same component set still moves citation rates in the intended direction, indicating that the underlying mechanism is not dataset-specific. The results reveal a potential disconnect between the model's apparent reasoning and its internal computational pathway, suggesting that inline citations can create a false sense of security. --- ### Physics-Constrained Neural Surrogate for Domain Growth Prediction in Systems with Conserved Kinetics Authors: Vijay Yadav, Pallvi Pandey, Madhu Priya, Manish Dev Shrimali, Prabhat K. Jaiswal Published: 2026-06-09 Categories: cs.LG, cond-mat.soft arXiv: https://arxiv.org/abs/2606.26128v2 The spatiotemporal evolution of many physical, chemical, and biological systems is described by nonlinear partial differential equations (PDEs). Recently, deep neural network-based surrogate models have emerged as efficient alternatives to computationally expensive numerical PDE solvers. In this work, we propose a physics-constrained deep neural network as a surrogate model to learn the microstructural evolution of a binary mixture, in which conservation of the order parameter is imposed directly on the network output as a hard constraint. We train the model to accurately predict the time-evolution of phase separation in binary mixtures governed by the Cahn-Hilliard equation. We show that predictions from our trained surrogate model remain stable and accurate over long-time rollouts for both critical and off-critical mixtures and preserve the mixture composition throughout evolution. In contrast, a variant in which conservation is enforced only via a penalty term in the loss function drifts away from the initial composition and significantly loses predictive accuracy over the same rollout. This establishes that the hard constraint is essential for long-time stability and order parameter conservation. We also show that our model accurately captures the growth of domain size and is consistent with the Lifshitz-Slyozov domain-growth law. These results demonstrate the effectiveness of the proposed framework for modeling systems with conserved kinetics, and the construction extends directly to other systems with conserved quantities. --- ### Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics Authors: Vijay Yadav, Madhu Priya, Manish Dev Shrimali, Prabhat K. Jaiswal Published: 2026-06-09 Categories: cs.LG, cond-mat.soft arXiv: https://arxiv.org/abs/2606.26128v1 The spatiotemporal evolution of many physical, chemical, and biological systems is described by nonlinear partial differential equations (PDEs). Recently, deep neural network-based surrogate models have gained increasing interest as efficient alternatives to computationally expensive traditional numerical solvers. In this work, we propose an attention-based, physics-guided convolutional neural network as a surrogate model to learn the microstructural evolution of such systems. We train the model to accurately predict the full time-evolution of phase separation in binary mixtures governed by the Cahn-Hilliard equation. We show that predictions from our trained surrogate model remain stable and accurate over long-time rollouts for both critical and off-critical mixtures and preserve the mixture composition throughout evolution. We also show that our model accurately captures the growth of domain size and is consistent with the Lifshitz-Slyozov domain-growth law. The prediction results demonstrate the effectiveness of the proposed framework for modeling systems with conserved kinetics and can be extended to other complex dynamical systems. --- ### Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier Authors: Kaiwen Shi, Zheyuan Zhang, Han Bao, Colby Nelson, Yanfang Ye Published: 2026-06-09 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2606.20662v1 Modern agent systems can turn uncertainty into overconfidence. Fragile upstream decisions are often exposed to downstream components as clean intermediate artifacts, while the uncertainty behind those decisions is lost at the interface. As a result, local ambiguity can become system-level error amplification. We argue that this reveals an interface bottleneck in agent uncertainty propagation: uncertainty does not propagate simply because a trajectory contains uncertain steps; it propagates only when it survives the handoff between components. We define uncertain decision handoff as the transfer of an intermediate decision made under uncertainty, and identify confidence laundering as a failure mode in which fragile upstream states are repackaged as procedurally valid artifacts that downstream agents over-trust. To address this bottleneck, we propose latent uncertainty as an uncertainty-bearing carrier attached to decision handoffs. Rather than replacing text with hidden states, latent uncertainty aims to preserve pre-commitment fragility in a form that downstream components can use. This position shifts agent uncertainty propagation from step-wise uncertainty estimation toward uncertainty-preserving interface design for more recoverable agent systems. --- ### From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents Authors: Yifan Li, Shengbin Yue, Boyu Feng, Jinhu Qi, Bo Ke, Zixing Song, Hongru Wang, Zhongyu Wei, Irwin King Published: 2026-06-09 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.20661v1 The integration of external tools has transitioned LLM agents from passive responders to autonomous systems. However, current benchmarks prioritize execution success, neglecting self-awareness capability, the ability to discern whether a problem requires necessary external resources or can be solved via internal parametric knowledge. To address this, we introduce KAPRO (Knowing-Acting Quadrant PRObe), a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting). We further construct KAware, a dataset rigorously partitioning tasks into external, internal, and hybrid subspaces to systematically probe these epistemic boundaries. Extensive experiments across diverse agent architectures show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings. Moreover, open-source and instruction-following models exhibit stronger tool overuse due to shallow pattern matching, while proprietary and reasoning-oriented models demonstrate more reliable cognitive gating. Benchmark and codes are available at https://github.com/AI-Santiago/KAware. --- ### Skill Coverage: A Test Adequacy Metric for Agent Skills Authors: Boyin Tan, Xiaowei Huang, Youcheng Sun Published: 2026-06-09 Categories: cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2606.20659v2 Agent skills encode reusable procedural knowledge for large language model (LLM) agents, and existing benchmarks show that such skills can improve task-level performance. However, a task outcome does not reveal which parts of a reusable skill were exercised, nor whether the agent followed the relevant skill instructions when those parts were exercised. This gap makes it unclear whether a skill has been adequately tested, or whether observed task failures provide actionable evidence for improving agent skill effectiveness. To fill this gap, we introduce skill coverage, a trajectory-based test-adequacy metric for reusable agent skills. Our framework extracts skill behavior constraints from each skill, translating natural-language skill instructions into semi-structured constraints that specify the expected agent behavior under particular conditions. It then determines whether each constraint is covered by an agent trajectory and, for covered constraints, assigns a Pass or Fail verdict according to the agent behavior. We apply this framework to SkillsBench. The results show that agent trajectories on the benchmark leaderboard cover only 38.66 to 45.51% of the extracted skill behavior constraints on average. We then use Fail verdicts to strengthen the corresponding skill content only by emphasizing the original instructions that the agent failed to follow, and run the same tasks with the strengthened skills. This emphasis yields an average 16.0% recovery rate of the failed tasks across the five agent-model rows. These results show that skill coverage is both a test-adequacy metric and a fine-grained signal for observing skill-use behavior. In failed tasks, failed constraint labels provide actionable evidence for improving agent skill effectiveness. A project website accompanies the paper. --- ### Expected Free Energy-based Planning as Variational Inference Authors: Wouter W. L. Nuijten, Thijs van de Laar, Bert de Vries Published: 2026-06-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20658v1 Planning under uncertainty requires agents to balance goal achievement with information gathering. Active inference addresses this through the Expected Free Energy (EFE), a cost function that unifies instrumental and epistemic objectives. However, existing EFE-based methods typically employ specialized optimization procedures that are difficult to extend or analyze. In this paper, we show that EFE-based planning can be formulated as Variational Free Energy minimization on a generative model augmented with epistemic priors. Our main result demonstrates that minimizing a Variational Free Energy functional with appropriately chosen priors yields a decomposition into expected plan costs (the EFE) plus a complexity term. This formulation reinforces theoretical consistency with the Free Energy Principle by casting planning as the same inferential process that governs perception and learning. We validate our approach on three environments of increasing complexity: a deterministic T-maze, a stochastic Reactivity Maze, and a partially observable MiniGrid DoorKey-8x8 environment. The experiments demonstrate that the epistemic priors induce information-seeking behavior, that the variational formulation yields policy-based inference outperforming plan-based methods under stochastic transitions, and that temporal factorization enables scalability to environments where existing tabular active inference methods cannot operate. --- ### A-Evolve-Training: Autonomous Post-Training of a 30B Model Authors: Zhan Shi, Bing He, Yisi Sang, Benoit Dumoulin, Hanqing Lu Published: 2026-06-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20657v3 Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous system that runs this loop with no human in the loop, post-training a 30B Nemotron across four rounds over multiple weeks. The autonomously produced model reaches a held-out score of 0.86 against the top human submission's 0.87 on the public NVIDIA Nemotron-Reasoning Challenge leaderboard, placing 8th of ~4000 at the time of writing. More striking than the number: the loop detected that its own dev metric had stopped tracking external performance on the weakest domain -- candidates drove dev to record highs without moving the external target -- and revised its own search policy, no longer maximizing dev but seeking interventions that lowered the now-misleading proxy while improving the external target. We treat this as direct, auditable evidence that a scaled autonomous loop can produce discovery, not only optimization: it detected that its measurement frame had become misleading and changed what counted as evidence. We take the operational view that any system worth the "recursive self-improvement" label must eventually perform end-to-end post-training of a frontier-class model; this is one datapoint of that bar being cleared. We do not claim a "first autonomous match" of human researchers. The claim we make is narrower and auditable: to our knowledge, this is the first publicly reported autonomous post-training run at this scale, where prior public autonomous-ML-research demonstrations sit at GPT-2-class (~124M) budgets. The same system also post-trains the 120B and 550B Nemotron; with no public human baseline there, this shows only that the loop closes at that scale, not that its output is competitive -- infrastructure evidence, with the effectiveness claim deferred until a comparable human anchor exists. --- ### A-Evolve-Training: Autonomous Post-Training of a 30B Model Authors: Zhan Shi, Bing He, Yisi Sang, Hanqing Lu, Benoit Dumoulin Published: 2026-06-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20657v2 Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous system that runs this loop with no human in the loop, post-training a 30B Nemotron across four rounds over multiple weeks. The autonomously produced model reaches a held-out score of 0.86 against the top human submission's 0.87 on the public NVIDIA Nemotron-Reasoning Challenge leaderboard, placing 8th of ~4000 at the time of writing. More striking than the number: the loop detected that its own dev metric had stopped tracking external performance on the weakest domain -- candidates drove dev to record highs without moving the external target -- and revised its own search policy, no longer maximizing dev but seeking interventions that lowered the now-misleading proxy while improving the external target. We treat this as direct, auditable evidence that a scaled autonomous loop can produce discovery, not only optimization: it detected that its measurement frame had become misleading and changed what counted as evidence. We take the operational view that any system worth the "recursive self-improvement" label must eventually perform end-to-end post-training of a frontier-class model; this is one datapoint of that bar being cleared. We do not claim a "first autonomous match" of human researchers. The claim we make is narrower and auditable: to our knowledge, this is the first publicly reported autonomous post-training run at this scale, where prior public autonomous-ML-research demonstrations sit at GPT-2-class (~124M) budgets. The same system also post-trains the 120B and 550B Nemotron; with no public human baseline there, this shows only that the loop closes at that scale, not that its output is competitive -- infrastructure evidence, with the effectiveness claim deferred until a comparable human anchor exists. --- ### Learning Splitting Heuristics for Parallel String Solvers Authors: Chenhao Gao, Peisen Yao Published: 2026-06-09 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.20656v1 String constraint solvers are crucial for reasoning about string-manipulating programs. However, many practical string constraints are undecidable, and real-world applications often present complex constraints that challenge current solvers. The rise of multi-core architectures offers an opportunity for parallel solving. A key parallel solving method is \emph{cube-and-conquer}, in which the quality of splitting heuristics is critical to effectively dividing the search space. Unfortunately, manually designing the heuristics is labor-intensive, and handcrafted heuristics are often sub-optimal. This paper introduces a data-driven approach to automatically generating splitting heuristics. We frame the problem of selecting a splitting atom as a learning task, using features from input formulas and dynamic data from solver execution. We implement this approach in two popular string solvers, Z3seq and Z3str4, demonstrating that the learned heuristics outperform manually designed ones in the number of solved formulas and the average solving time. --- ### Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing Authors: Yongchao Huang, Hassan Raza Published: 2026-06-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.18283v1 The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \textbf{Gaussian Mixture Attention (GMA)}, a probabilistic attention-style sequence mixer that replaces explicit pairwise query--key comparison with routing through $K$ learned Gaussian mixture components. Queries and keys are mapped to posterior \textit{responsibility} vectors over a shared latent routing space; their overlap defines an implicit responsibility-space affinity, while values are written into and read from a $K$-slot latent memory. By exploiting the associativity of matrix multiplication, GMA avoids materializing the induced $N\times N$ affinity matrix and instead uses two responsibility matrices whose dominant activation storage scales as $\mathcal{O}(NK)$ rather than $\mathcal{O}(N^2)$ for fixed $K$. We formulate bidirectional and causal variants of GMA, provide an end-to-end differentiable parameterization of the Gaussian mixture components, and analyze its responsibility-modulated gradient structure, constrained non-negative low-rank affinity interpretation, and local routing stability. Empirically, GMA exhibits the intended fixed-$K$ linear memory scaling and is competitive with attention-style baselines on long-context classification, while causal GMA improves over tested linear/random-feature attention variants on WikiText-103 but remains behind optimized causal SDPA and Mamba in the current implementation. Analysis of learned responsibilities further shows broad component usage and moderate alignment with surface-form token categories, supporting GMA as a probabilistic, interpretable, fixed-$K$ linear-time attention-style alternative rather than a universal replacement for optimized softmax attention or state-space models. --- ### Double-Helix Vision (DH-V2): A Geometry-Based Visual Sampler for Bandwidth-Constrained Perception Authors: Jinwen Wen Published: 2026-06-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14773v1 We present Double-Helix Vision (DH), a geometry-based visual sampler that compresses 2D images into compact 1D signals using paired golden-ratio-inspired spiral trajectories. Rather than processing every pixel uniformly, DH employs two phase-shifted helices (Alpha and Beta, offset by 180 degrees) to sample the image with biologically-inspired foveation: high density at the center, sparse coverage at the periphery. At 4K resolution, DH achieves a 1,433x compression ratio (99.93% reduction) while preserving the geometric structure of the scene. The full perception pipeline -- including spatial mapping, temporal collision detection, and intra-frame structural disparity estimation -- runs in 0.52 ms at 1080p on CPU-only hardware, with no neural network dependencies. On CIFAR-10 at extreme sampling budgets (K=128 points per helix), DH achieves a +6.03% accuracy gain over uniform random sampling. A JSON-serializable Robotics API is provided, delivering sub-millisecond spatial perception reports in 2.7 KB packets. Code and benchmarks are available under the MIT License. --- ### ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering Authors: Wenhao Lu, Zhengqiu Zhu, Xiaofeng Wang, Xiaoran Zhang, Yatai Ji, Yong Zhao, Yue Hu, Yingzhen Nie, Jinlong Zhu, Zheng Zhu Published: 2026-06-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14772v1 Aerial Embodied Question Answering (EQA) requires Unmanned Aerial Vehicles (UAVs) to actively perceive the environment and answer natural language questions. Existing outdoor EQA systems usually stop once the target enters the UAV's field of view, leaving the fine-grained viewpoint adjustment needed for evidence-seeking questions largely unresolved. To address this issue, we introduce FG-EQA, a fine-grained active perception EQA benchmark with more than 40K simulated trajectories and 1K real-world trajectories. Drawing inspiration from the ``waggle dance'' of scout bees, which iteratively adjust their flight paths to verify target information, we propose ScoutVLA, an evidence-driven Vision-Language-Action model for outdoor EQA. To emulate this active exploration behavior, ScoutVLA features a decoupled dual-expert architecture: a vision-language expert infers the semantic intent to identify missing evidence, while an independent action expert employs high-DoF flow matching to generate continuous viewpoint-refinement trajectories. To balance the competing demands of continuous control and semantic reasoning, we devise a decoupled training strategy with a knowledge insulation mechanism that prevents the action gradients from erasing the model's multimodal reasoning ability. Extensive simulated experiments and a qualitative real-world field study both verify the superiority of ScoutVLA over the state-of-the-art baselines, demonstrating a 10.48$\boldsymbol{\times}$ higher average strict success rate and a 7.72$\boldsymbol{\times}$ higher average QA correctness. --- ### An Empirical Analysis of Optimization Dynamics and Sparsity Boundaries in Large-Scale Pedestrian Attribute Recognition Authors: Houssam El Mir Published: 2026-06-09 Categories: cs.CV, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.14770v1 Pedestrian Attribute Recognition (PAR) is critical for video surveillance, enabling forensic search and re-identification systems. Extreme class imbalance remains a fundamental obstacle when merging PETA and PA-100K into a 109,000-image composite corpus, where minority attributes have positive sample fractions below 1%. This causes standard BCE optimization to suppress rare traits, a phenomenon we term the majority negative class cheating trap. We present a systematic ablation of Multi-Label Focal Loss hyperparameters (alpha and gamma) on a ResNet-18 backbone. A calibrated configuration (alpha=0.50, gamma=2.0) achieves a Macro F1-score of 62.32%, matching BCE baseline while preserving superior hard-example mining and convergence dynamics. Our approach uses pure loss-function engineering with zero computational overhead for edge deployment. We identify the Sparsity Wall, a hard boundary where positive sample fractions below 0.1% make global loss reweighting ineffective, requiring instance-level intervention. --- ### Agentomics: Economic Foundations for the Valuation, Attribution, and Pricing of AI Agents in Human-AI Workflows Authors: Quanyan Zhu Published: 2026-06-09 Categories: econ.EM, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2606.14769v1 Agentic AI systems are increasingly being deployed as productive resources in organizational workflows, yet existing evaluation methods primarily measure isolated technical performance rather than economic contribution. This paper introduces \emph{Agentomics}, a workflow-based framework for valuing, attributing, and pricing human and artificial agents. The framework models a workflow as a configuration of heterogeneous agents whose collective performance determines gross value, deployment cost, reliability, and expected failure loss. Workflow value is treated as a team-level quantity that may include complementarities, substitution effects, bottlenecks, and nonlinear production; additive stage-level value is only a special case. Building on this workflow model, the paper formulates AI deployment as a coalition-formation problem and defines coalition value as the incremental net surplus generated relative to a benchmark human workflow. The Shapley value is then used to attribute economic surplus among participating AI agents, yielding a principled connection among valuation, accountability, and market pricing. The resulting Shapley pricing equilibrium provides a normative benchmark for assessing whether agent prices reflect expected marginal contribution. A security-operations case study illustrates how the framework accounts for productivity gains, deployment costs, reliability losses, and coalition-level complementarities in hybrid human--AI workflows. --- ### HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification Authors: Maohua Nie, Jiang Zhu, Jingqun Zhang, Zhichen Zeng, Jiayi Wang, Sibo Zhang, Jialin Wang, C. -J. Richard Shi Published: 2026-06-09 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2606.13706v1 We present HierSVA, an integrated suite that combines a pipeline, dataset, and benchmark for LLM-driven hierarchical hardware formal verification. HierSVA-SP pairs an RTL preprocessing toolchain with an LLM-in-the-loop formal verification flow to produce reference SystemVerilog Assertions (SVA) on hierarchical RTL. Applying it to BaseJump STL yields HierSVA-DS, a dataset of 342 modules, with hierarchy metadata and depths 0--9, accompanied by a deep subset of 28 module-bug pairs with natural-language specifications and bug variants. HierSVA-B decomposes assertion quality into six metric axes: syntax correctness, assertion proof success rate, vacuity, specification faithfulness, mutation coverage, and formal core coverage. Applying HierSVA-B to twelve recent LLMs reveals three findings. First, the module-level compile rate is 67.1\%; among generated assertions in evaluable runs, 82.1\% prove non-vacuously, but the corresponding assertion sets detect only 70.2\% of eligible injected faults and cover 36.2\% of the formal core. Second, on 211 evaluable model--module entries in the deep subset, assertion sets flag buggy RTL with 0.87 recall, but 40\% of predicted-buggy outcomes are false positives on correct RTL, limiting precision to 0.60. Third, agentic mode improves S1-style provability and strength metrics, but gains plateau and oscillate. Codes and artifacts are available at \href{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}{https://github.com/HierSVAAnon/HierSVACodeAndArtifacts}. Dataset is available at \href{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}{https://huggingface.co/datasets/AnonymousHierSVA/HierSVA}. --- ### When Can One Neuron Fix Repetition Loops in LLMs? Authors: Aristotelis Lazaridis, Aman Sharma, Dylan Bates, Brian King, Vincent Lu, Jack FitzGerald Published: 2026-06-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.13705v2 The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as TV episodes, the 88 IAU constellations, or the 151 original Pokemon, they collapse into repetition, either a tight verbatim loop or a list whose entries decay onto one answer. These loops reach 87.5% (7/8 generations) and survive prompt rewording and most sampling adjustments. In this paper, we explore whether edits to a few internal model components can directly reduce this failure, without relying on repetition penalties, which can distort valid repetition and degrade task performance. To locate such targets, we combine per-layer ablation with per-neuron or routed-expert attribution, then evaluate weight edits over complete generations. We find that these edits substantially reduce detected loops on the prompts and seeds used to select them; in Gemma 4 E2B, for example, one sign-inverted neuron suffices. Across all four Gemma models, detected loops fall from 46/384 to 12/384 on frozen held-out prompts and seeds, driven mainly by E4B and 31B, while general-purpose benchmarks show no statistically detectable regressions. Our attribution methodology identifies useful candidates, but rankings vary across examples. At longer generation budgets, edits remain effective for E2B and E4B, whereas remaining failures in 26B and 31B shift toward doom looping: non-convergent self-correction over facts the model cannot recall. In exploratory experiments on Qwen3.5 and LFM2.5, sparse edits also reduce repetition, providing preliminary cross-family evidence, although effect strength and selectivity vary. Overall, our results show the promise and limits of targeted, small-scale weight editing: it can suppress specific repetition failures and provide a training-free causal intervention, but does not reveal a universal loop circuit, guarantee clean termination, or supply missing knowledge. --- ### Can Editing 1 Neuron Fix Repetition Loops in LLMs? Authors: Aristotelis Lazaridis, Aman Sharma, Dylan Bates, Brian King, Vincent Lu, Jack FitzGerald Published: 2026-06-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.13705v1 Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as listing every episode of a TV series, the 88 IAU constellations, or the 151 original Pokemon, they collapse into repetition, either a tight verbatim loop or a list whose entries decay onto a single answer. These loops occur at rates as high as 95% and survive prompt rewording, inference-engine changes, and most sampling adjustments. In this paper we explore whether this behavior is localized enough to remove by weight edits. To localize the cause, we use per-layer ablation and per-neuron attribution, then confirm the strongest candidates with full-generation sweeps. The loops trace to a small set of MLP neurons (or, in the 26B-A4B Mixture-of-Experts model, a few routed experts) which we suppress with static weight edits. These "surgeries" can be as small as a single sign-inverted neuron (in the E2B model). The size of the effective edits grows with model scale, but in all cases, the loop patterns can be addressed at normal generation budgets while preserving general-purpose benchmark scores. However, the edits do not solve everything: we also study longer thinking budgets, where the two larger models most visibly enter doom looping, i.e. a non-convergent regime in which the model self-corrects in circles over a fact it cannot recall, exhausting the budget without committing to a final answer. We show this residual failure is reduced but not eliminated by the same edits, and argue it is fundamentally a knowledge-precision problem rather than a removable circuit; weight surgery can delete a loop, but it cannot supply a missing fact. Our results are both a feasibility demonstration, that is, evidence that a concrete generation pathology can be localized to a few parameters and edited out, and a delineation of where that approach stops. ---