# Research Papers — 2026-06 · bundle page 245 of 260 > Full-text markdown of papers #12201–12250 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/245 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/244.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/246.md) ### HyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift Authors: Yu-Kai Chan, Wen-Sheng Lien, Dong-Ting Yao, Bo-Kai Ruan, Kwan-Yeung Lin, Hong-Han Shuai, Meng-Fen Chiang Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03179v1 Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-world knowledge is inherently n-ary. We demonstrate that in non-stationary environments, sequential updates to complex relations induce N-ary Structural Drift, a phenomenon where the binary reification of n-ary events into triples fractures relational atomicity. This precipitates Structure-Conditioned Knowledge Transfer Failure, a systematic mis-grounding of the retriever frequently misdiagnosed as parametric hallucination. To tackle this, we propose HyperPatch, a parameter-preserving framework that reformulates sequential KE as a stability problem over hypergraph manifolds. HyperPatch preserves event integrity through three phases: (i) Structural Prior Initialization, establishing a topology-aware embedding space via contrastive learning on a Hypergraph Neural Network (HGNN) to capture high-order correlations; (ii) Sequential Topology Editing, utilizing a dual-stage mechanism that employs SimHash-based Topological Alignment for rapid conflict resolution and Topological LoRA Adaptation to track drift without backbone retraining; and (iii) Structure-Conditioned Reasoning, which integrates globally consistent evidence from fused linguistic and structural manifolds. On the MQuAKE-CF and MQuAKE-T benchmarks, HyperPatch achieves relative gains in Hop-wise Accuracy (H-Acc) of 96.24% and 21.06% over the strongest baseline, respectively. Further ablations demonstrate superior reliability under continuous n-ary update streams, whereas the standard KG-based variant suffers H-Acc collapses of up to 88.3% due to structural misalignment. --- ### Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation Authors: Xunyi Zhao, Sihao Lin, Gengze Zhou, Zerui Li, Shijie Li, Wei Tao, Jiajun Liu, Qi Wu Published: 2026-06-02 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2606.03175v2 Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an under-specified natural-language description. Such ambiguity often cannot be resolved from perception and language alone, making interaction with an oracle a natural mechanism for disambiguation. Prior interactive methods allow oracle queries but treat lightweight clarification and route-level guidance alike, letting agents boost success rate through repeated high-information questions rather than by resolving the underlying ambiguity efficiently. We recast interactive IGN as a cost-sensitive uncertainty-reduction problem, where the agent should ask the question whose answer provides the largest reduction in navigation uncertainty relative to its penalty. To this end, we apply an information-gain analysis on existing navigation corpora to identify which cues reduce navigation uncertainty, yielding a compact set of question types and data-derived weights. However, existing interactive navigation benchmarks do not model the cost of different question types or evaluate how efficiently agents use interaction, making them unsuitable for studying cost-sensitive interaction. Based on this taxonomy, we construct a benchmark for diagnosing interaction behavior and efficiency, together with a Weighted Success Rate metric that penalizes each query by its derived cost. We further propose a zero-shot MLLM navigator that selectively queries at each decision step only when the expected uncertainty reduction justifies the interaction cost. --- ### Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach Authors: Zijing Wei, Chao Peter Yang, Xuanjie Chen Published: 2026-06-02 Categories: cs.CY, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2606.03173v1 The rise of `kidfluencers' on YouTube has raised ethical concerns about child digital labor and exploitation. While emerging legislation attempts to regulate this ecosystem, empirical evidence linking exploitation to engagement remains scarce, given the difficulty of operationalizing exploitation at scale. This study presents a multimodal AI audit of 5,051 videos across 79 kidfluencer channels, using weak supervision to detect exploitation signals without large-scale manual labels. We aggregate noisy labeling functions -- including LLM-based classification of titles and GPT-4 Vision analysis of thumbnails and descriptions across six literature-grounded dimensions -- to assign a probabilistic exploitation score to each video. A multi-annotator validation study (N=107) shows strong agreement with human judgment (macro-average F1 $= 0.911$) and high sensitivity for overall exploitation risk (recall $= 0.960$, F1 $= 0.793$). Our findings reveal a significant engagement premium for performative labor, emotional bait, and privacy violations. Exploitation scores correlate with view counts (Spearman $ρ= 0.229$, $p < 10^{-50}$), and mixed-effects regression controlling for channel-level variation shows that a one-unit increase in exploitation score yields a $4.4\times$ increase in views ($p < 0.001$). Within-channel analyses indicate median view boosts of $+65.6\%$ for emotional bait and $+56.0\%$ for performative content (FDR-corrected $p<0.001$), with effects holding in same-year robustness checks ($p=0.030$). Explicit commercial content (product placement), by contrast, shows no premium ($-3.8\%$, n.s.), suggesting the platform rewards commodification of the child's identity and labor over traditional advertising. These findings challenge policy frameworks focused solely on financial trusts, showing that engagement is systematically tied to the intensive, performative labor of children. --- ### SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling Authors: Xiaoyue Duan, Nanxing Hu, Yutang Feng, Xudong Yan, Jiatao Chen, Jinchao Zhang, Jie Zhou Published: 2026-06-02 Categories: cs.SD, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.03169v1 Recent song generation systems can synthesize realistic audio, yet generating complete songs remains challenging for two reasons. First, explicit song-level arrangement planning remains limited in existing methods, so models often need to organize overall arrangement development while generating low-level audio details. This often leads to incoherence in arrangements, such as weak section transitions and limited dynamic progression. Second, coarse modeling of different musical parts obscures their distinct roles and interactions, limiting arrangement richness of generated songs. In this paper, we present SketchSong, a hierarchical song generation framework that addresses these issues through song-level sketch planning and fine-grained multi-track modeling. Along the temporal dimension, SketchSong first predicts a compact sequence of high-level sketch tokens derived from compressed audio representations, and then generates audio tokens conditioned on these sketches. This coarse-to-fine process gives the model an explicit arrangement plan before detailed audio generation. Along the track dimension, SketchSong explicitly models four tracks, i.e., vocals, bass, drums and other instruments. This enables the model to capture the roles and interactions of different musical parts more precisely. Experiments on song generation benchmarks show that SketchSong consistently outperforms our baseline on both objective metrics and human listening tests. Despite not employing additional post-training for preference optimization such as lyrics and text-prompt alignments, SketchSong achieves competitive results against strong, post-trained open-source systems, demonstrating the effectiveness of our overall design. --- ### JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation Authors: Yinan Chen, Chuming Lin, Zhennan Chen, Yuxiang Zeng, Junwei Zhu, Yali Bi, Xijie Huang, Chengming Xu, Donghao Luo, Zhucun Xue, Xiaobin Hu, Chengjie Wang et al. Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03168v1 While instruction-based video editing has seen significant progress, joint audio-visual editing remains constrained by the absence of dedicated datasets and benchmarks. To bridge this gap, we present JAVEdit-100k, the first large-scale, high-quality dataset tailored for instruction-guided joint audio-visual editing. Focusing on human-centric videos, JAVEdit-100k comprises approximately 100K editing triplets spanning five distinct categories, including subject editing and speech editing. This dataset is rigorously constructed via four meticulously designed generation pipelines, seamlessly paired with an agent-in-the-loop quality control mechanism. Furthermore, to address the lack of standardized evaluation within the field, we introduce JAVEditBench, a comprehensive benchmark featuring curated source videos and human-aligned instructions across all editing categories. Finally, we propose JAVEdit, a pioneering baseline model for instruction-guided joint audio-visual editing. Experiments show that \model\ outperforms all baselines on five of six evaluation metrics. --- ### Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models Authors: Thomas Stephan Juzek, Xiaoyang Ming, Jose A. Hernandez Published: 2026-06-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.03165v1 The language used by digital chat assistants such as ChatGPT can diverge from human expectations (misalignment). Research, mostly on Scientific English, has described both what divergences occur and, to some extent, why, linking them to the training stage of human preference learning. Yet, existing approaches rely on manual curation. This paper introduces two curation-free, assumption-light evaluation metrics: the Lexical Alignment Score, which identifies lexical overuse, and the Triangulated Preference Shift, which quantifies how much of such shifts can be attributed to human preference learning. Using PubMed abstracts, continuations were generated and measured using windowed document prevalence across six model families (Falcon, Gemma, Llama, Mistral, OLMo, Yi). The procedure identifies, without manual intervention, overused items such as 'suggest', 'additionally', and 'strategy', and estimates their link to preference learning. Our findings replicate prior work and remain stable across parameter settings, random seeds, and evaluation on further data. The approach scales readily and enables systematic study of lexical (mis)alignment beyond Scientific English and across languages, and as such, the metrics have the potential to contribute to improved alignment for future models and understanding of its origins. --- ### OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery Authors: Jinliang Xu Published: 2026-06-02 Categories: cs.MA, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2606.03163v4 This yellow paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection and discoverable AI resource products. It specifies the role architecture, \texttt{did:oan} identity objects, registration workflow, governance-backed Root lifecycle enforcement, Root-verified package model, authorization-aware Discovery, Root-issued infrastructure authorization VCs, signed trusted invocation, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, domain-specific Agent protocols, Skills, MCP Servers, and Tool/API resources. OAN does not define the entire business conversation among Agents or the native protocol of every resource; it defines how resource identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins. --- ### OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery Authors: Jinliang Xu Published: 2026-06-02 Categories: cs.MA, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2606.03163v3 This yellow paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection and discoverable AI resource products. It specifies the role architecture, \texttt{did:oan} identity objects, registration workflow, governance-backed Root lifecycle enforcement, Root-verified package model, authorization-aware Discovery, Root-issued infrastructure authorization VCs, signed trusted invocation, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, domain-specific Agent protocols, Skills, MCP Servers, and Tool/API resources. OAN does not define the entire business conversation among Agents or the native protocol of every resource; it defines how resource identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins. --- ### OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection Authors: Jinliang Xu Published: 2026-06-02 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2606.03161v4 OpenAgenet, abbreviated as OAN, is an open infrastructure project for trusted Agent interconnection. It addresses a problem that becomes visible when Agents move from isolated applications into open, multi-operator networks: before an Agent can safely discover, select, and invoke another Agent, it needs a way to verify identity provenance, governance state, discovery authorization, freshness, and pre-connection trust evidence. OAN is designed as a protocol-neutral trust layer. It does not replace Agent interaction protocols, tool protocols, model orchestration frameworks, or application-level workflows. Instead, it provides \texttt{did:oan}-based resource identity, governance-backed admission, Registrar-assisted onboarding, Root-verified package publication, authorization-aware Discovery, Root-issued infrastructure authorization VCs, and signed trusted invocation. The architectural center of OAN is the combination of federated governance, resource identity, and trusted Discovery, rather than a single directory or naming service. This white paper explains the motivation, architecture, roles, governance model, relationship with MCP, A2A, and ANP, deployment patterns, cooperation model, on-chain governance layer, prototype status, performance profile, and roadmap of OAN. --- ### OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection Authors: Jinliang Xu Published: 2026-06-02 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2606.03161v3 OpenAgenet, abbreviated as OAN, is an open infrastructure project for trusted Agent interconnection. It addresses a problem that becomes visible when Agents move from isolated applications into open, multi-operator networks: before an Agent can safely discover, select, and invoke another Agent, it needs a way to verify identity provenance, governance state, discovery authorization, freshness, and pre-connection trust evidence. OAN is designed as a protocol-neutral trust layer. It does not replace Agent interaction protocols, tool protocols, model orchestration frameworks, or application-level workflows. Instead, it provides \texttt{did:oan}-based resource identity, governance-backed admission, Registrar-assisted onboarding, Root-verified package publication, authorization-aware Discovery, Root-issued infrastructure authorization VCs, and signed trusted invocation. The architectural center of OAN is the combination of federated governance, resource identity, and trusted Discovery, rather than a single directory or naming service. This white paper explains the motivation, architecture, roles, governance model, relationship with MCP, A2A, and ANP, deployment patterns, cooperation model, on-chain governance layer, prototype status, performance profile, and roadmap of OAN. --- ### SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition Authors: Qiuxia Wu, Jiarui Lan, Wenxiong Kang, Zhiyong Wang, Kun Hu Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03160v1 Recognizing human actions from point cloud sequences is critical for 3D perception driven applications such as autonomous driving and human-computer interaction. However, the irregular structure and temporal inconsistency of point clouds pose unique challenges for spatio-temporal representation learning, especially in capturing both global motion context and fine-grained temporal dynamics. We propose SRENet, a spectral-aware framework designed to explicitly learn both global context and fine-grained temporal dynamics of motion from a frequency perspective for action recognition. SRENet introduces a Spectral Decomposition Block (SDeBlock) that performs wavelet-based analysis along temporal and spatial axes, disentangling features into low- and high-frequency components with frequency-specific attention. To recover residual dynamics and re-align temporal frequency structures distorted during semantic fusion, a Spectral Re-entry Block (SReBlock) performs secondary temporal decomposition. Furthermore, a spectral-aware learning strategy is devised to enhance discriminability in both frequency subspaces via contrastive loss and a curriculum schedule that gradually shifts focus from low- to high-frequency spaces in line with coarse to detailed motion patterns. Extensive experiments on MSR-Action3D, NTU-RGBD and NTU-RGBD120 demonstrate that SRENet achieves state-of-the-art performance, validating the effectiveness of frequency modeling in point cloud-based action understanding. --- ### NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Authors: Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas, Jay Zhangjie Wu, Jialiang Wang et al. Published: 2026-06-02 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.03159v3 As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures. --- ### NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Authors: NVIDIA, :, Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, Francesco Ferroni, Guillermo Garcia Cobo, Haithem Turki, Huan Ling, Jaewoo Seo, James Lucas et al. Published: 2026-06-02 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.03159v2 As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving policy model actively interacts with the environment, where its actions dynamically update the simulator state and directly influence the next set of generated sensor observations. While recent reconstruction-based neural simulators offer photorealism, they are fundamentally constrained by their initial captured data and struggle to generalize to highly dynamic or novel scenes. To overcome these limitations, we introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time. By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena that are hard for traditional simulators to capture, such as extreme weather and unpredictable dynamic agent behaviors. Crucially, it autoregressively conditions its photorealistic sensor generation on past frames, the current simulator state, and immediate driving actions. Deployed in a closed-loop system with the Alpamayo 1 policy model and AlpaSim orchestrator, OmniDreams acts as a highly responsive, reactive environment, providing a scalable and comprehensive solution for training and evaluating next-generation autonomous driving policies. We additionally show preliminary results indicating that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters. These results highlight the potential for a real-time world model like OmniDreams to also serve as a backbone for policy architectures. --- ### ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models Authors: Ruihui Hou, Siyi Zhu, Ziyue Huai, Guangya Yu, Yongqi Fan, Chunming Wang, Tong Ruan Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03157v1 Large language models (LLMs) have been widely adopted in healthcare, yet they still encounter significant challenges in complex clinical decision-making scenarios. Existing benchmarks primarily assess LLM performance in single-course settings and lack systematic evaluation in multi-course scenarios, where a patient's condition evolves over time. To address this gap, we propose ClinicalMC, a benchmark for multi-course clinical decision-making. It includes 1,275 Chinese and 5,804 English samples across four stages from admission to discharge. These stages cover triage, first-course examination/diagnosis/treatment, subsequent multi-course examination/assessment/treatment, and final diagnosis. In ClinicalMC, patients in the English dataset undergo an average of 5.11 clinical courses, whereas those in the Chinese dataset undergo 3.42. To assess LLM performance, we construct a multi-agent evaluation framework that includes patient, examiner, and doctor agents. Based on the benchmark and framework, we design two experimental settings -- a single-turn static setting and a multi-turn dynamic setting -- and assess three categories of LLMs: 1) closed-source LLMs like GPT5-mini; 2) open-source LLMs like DeepSeek-V3.2; and 3) medical LLMs like HuatuoGPT-o1. Through extensive evaluation, we aim to better understand LLM performance in the medical domain and support its effective deployment in healthcare. --- ### A cross-domain tropical species dataset with Chinese vernacular names and CITES source links Authors: Jeff Wang Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03156v1 We describe a versioned cross-domain dataset of 410,499 active tropical species (working snapshot 2026-04-20) spanning three applied subdomains -- tropical_plants, tropical_aquatic, and tropical_pets -- that share a commercial and regulatory life cycle but are distributed across kingdom-organised biodiversity infrastructures. The resource joins taxonomic identifiers from GBIF, Plants of the World Online, iNaturalist, NCBI Taxonomy, the Catalogue of Life and the Encyclopedia of Life, and adds three original layers: a cross-domain ontology that re-segments taxa along trade and husbandry contexts; a Chinese vernacular layer with explicit per-name provenance under a typology that excludes unverified machine-generated proposals; and a CITES source-linkage layer connecting each taxon to its Species+ entry. Chinese vernacular coverage -- the proportion of taxa carrying a CJK Chinese name distinct from the scientific binomial -- reaches 99.50 percent (408,456 of 410,499; full-population count). Coverage characterises completeness, not name-translation accuracy; the latter is bounded by the four-level provenance typology and is the subject of a preliminary internal review reported here, with a blind external audit identified as the principal open item. Upstream content is referenced by stable identifier only for the original-contribution layers, supporting CC-BY 4.0 reuse. The dataset is deposited on Zenodo (10.5281/zenodo.20377811). This preprint is the canonical v1.0 description of the dataset's current state; future Data Descriptor submission is anticipated but is contingent on the validation and release-engineering items listed in the Limitations. --- ### $A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones Authors: Sreehari Rammohan, Huy Ha, Carl Vondrick Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03148v1 Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ViTs. However, we still need large ViTs, because they extract richer representations from each patch. To get the best of both worlds, good localization and rich representations, we propose $A^2$, a simple method that leverages this inverse scaling finding by decoupling where to look (a small attention model) from what to extract (a large embedding model): we crop around the attention peaks of a small model and embed the crops with a larger model. $A^2$ uses entirely pretrained features, requires no group labels, and does not require per-dataset attention or backbone training. Across 5 benchmarks, $A^2$ is competitive with backbone-matched loss-level methods like DFR, and outperforms end-to-end attention training under stronger distribution shifts. --- ### GTBench: A Curriculum-Grounded Benchmark for Evaluating LLMs as Mathematical Research Assistants in Graph Theory Authors: Noujoud Nader, Ibrahem Aljabea, Patrick Diehl, Deepti Gupta Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03144v1 Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning assistants remains poorly understood. We introduce GTBench, a curriculum-grounded benchmark for evaluating LLMs as mathematical research assistants in graph theory, comprising 63 problems organized into three groups of increasing difficulty: undergraduate definitions and basic properties (Group 1), algorithm tracing and structural reasoning (Group 2), and graduate-level proof construction (Group 3). Problems are sourced from verified academic materials including Diestel's Graph Theory. We evaluate five frontier models -- GPT-5, Claude Sonnet 4.6, Gemini 2.5 Flash-Lite, Llama 3.3 70B, and Mistral Large 3 -- under zero-shot and chain-of-thought prompting, using exact-match and LLM-as-judge evaluation for Groups 1 and 2, and a hybrid human expert and LLM-as-judge protocol for Group 3. Our results reveal a pronounced performance hierarchy: GPT-5 approaches ceiling on Group 1 (95.8% zero-shot) and maintains meaningful accuracy on graduate proofs (82%), while all other models degrade substantially with difficulty, with Llama achieving 0% under human evaluation on Group 3 zero-shot. Failure mode analysis shows that correct algorithm, wrong execution errors dominate Groups 1 and 2, while Group 3 additionally surfaces incomplete reasoning failures and reveals systematic disagreement between human evaluators and the automated judge, particularly on verbose or near-complete proofs (kappa = 0.48-0.83 across human pairs). GTBench provides the first curriculum-grounded evaluation framework for graph-theoretic reasoning in LLMs, with direct implications for the governance of AI tools in mathematical education and scientific research. --- ### FederatedSkill: Federated Learning for Agentic Skill Evolution Authors: Jingbo Yang, Guanyu Yao, Yang Zhang, Ramana Rao Kompella, Gaowen Liu, Shiyu Chang Published: 2026-06-02 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.03143v1 Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement. However, isolated single-user task streams lack the diversity required to build comprehensive skills. While cross-user collaboration can overcome this data bottleneck, current trajectory-sharing approaches compromise user privacy and impose a uniform global library that fails to accommodate client heterogeneity. We introduce FederatedSkill, a privacy-preserving framework for collaborative agent evolution. Moving beyond raw trajectory sharing, FederatedSkill utilizes semantic skill diffs, structured patches over local libraries, as the fundamental unit of communication. On the server side, an evolution agent aggregates these patches to dynamically model client-specific capability boundaries, facilitating strictly personalized skill evolution rather than a suboptimal global average. Evaluated across 20 distinct agent task families, FederatedSkill demonstrates substantial gains over self-evolving baselines, achieving up to a 44.4% increase in success rate and a 37.5% reduction in computational cost. --- ### Disentangling Visual and Factual Correctness in LVLMs' Visualization Literacy Authors: Soohyun Lee, Jaeyoung Kim, Seokhyeon Park, Sihyeon Lee, Jiwon Song, Bohyoung Kim, Hyunjoo Song, Jinwook Seo Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03142v1 Large Vision-Language Models (LVLMs) show strong visualization interpretation, yet it is unclear whether their responses reflect genuine reasoning over visual evidence or factual priors learned during training. Current evaluations mix these two sources, obscuring when correct visual interpretation is overridden by memorized facts. We present a framework that isolates visual correctness from factual correctness, revealing validity limitations in existing visualization literacy assessments. Across three experiments with 15 state-of-the-art LVLMs: (1) several models reach human-level performance on standard tests (VLAT), but this may reflect factual recall rather than visual understanding, while randomized-data tests (reVLAT) underestimate literacy when correct visual interpretation is superseded by factual priors. (2) Using our Counterfactual Visualization Literacy Assessment Test (CVLAT) with capability-normalized arbitration metrics, we classify models by the sign of their visual-factual reliance index (VFRI), revealing a visualization-oriented majority and a factual knowledge-oriented minority, though several near-zero cases warrant caution. A human baseline (N=30) on the same counterfactual items confirms that people overwhelmingly follow the chart under conflict, providing a human reference point. (3) Prompt-based intervention can shift prioritization, but its effectiveness is highly model-dependent and direction-asymmetric, and high chart-reading capability does not predict prompt-controllability. Overall, high visualization accuracy is not sufficient evidence of faithful visual reasoning: reliable integration into visual analytics requires evaluating not only visualization literacy but also how models arbitrate between visual evidence and factual priors when the two diverge. Benchmark and code: https://github.com/JaeyoungKim-HCIL/CVLAT --- ### Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation Authors: Kaiqi Yang, Tai-Quan Peng, Sanguk Lee, Hui Liu Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03137v2 LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frameworks represent interaction mainly as observable turn exchange or aggregated outputs, leaving the internal evaluative processes behind silence, speaking intention, and public expression difficult to examine. We introduce TBS (Think-Before-Speak), an interval-based multi-agent simulation framework that separates agents' private reasoning from public utterance generation. At each interval, all agents update structured internal states based on the shared dialogue history and their own memory. These states include dissonance-related appraisal, perceived opinion climate, perceived isolation risk, response strategy, and willingness to speak. The orchestrator then resolves competing speaking intentions and commits one utterance to the public dialogue, allowing internal evaluation and public interaction to co-evolve over time. We evaluate TBS in simulated town hall discussions on a climate-related policy issue. Results show that TBS produces coherent internal-state traces and that these traces vary systematically across turn-allocation, silence, and memory conditions. Dissonance-related appraisal increases agents' willingness to speak, whereas silence-pressure appraisal decreases it. Once speaking intention is formed, public expression is shaped mainly by turn-allocation rules. These findings suggest that TBS supports mechanism-sensitive social simulation by making the pathway from internal evaluation to public expression observable and analyzable. --- ### PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations Authors: Muberra Ozmen, Subhabrata Majumdar Published: 2026-06-02 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2606.03136v1 Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails: they operate on individual turns, while attacks unfold as trajectories across conversations. We propose a shift from content to dynamics, modeling conversations as paths in representation space and asking whether adversarial intent is encoded early in their geometry. We introduce PsychoPass, a framework that extracts geometric features from conversation trajectories in embedding space to predict a potential attack before harmful content is produced. These features achieve near-perfect performance in naïve classifiers, which is largely explained by the inclusion of number of turns as a feature. After removing this confound, a smaller but consistent geometric signal remains, with classification performance that does not depend meaningfully on encoder choice. Crucially, this signal appears early in the conversation: attack outcomes remain above chance from short prefixes alone, more reliably than baseline guardrails. A supporting theoretical analysis explains these findings via a decomposition of length and shape, a detection bound based on prefix length, and encoder invariance. Together, these results show that adversarial conversations leave an early, representation-robust geometric fingerprint suitable for online monitoring. --- ### Uncertainty-Aware Clarification in LLM Agents with Information Gain Authors: Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Ying Zhao, Zhijiang Guo, Wei Wang Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03135v1 Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this challenge, we propose a goal-oriented clarification framework that aligns clarification behavior with ambiguity resolution. Central to our approach is the Information Gain Reward, a metric that quantifies the utility of clarification questions by measuring the Bayesian belief update towards the ground-truth goal induced by the clarification exchange. We train the clarifier (LLM) using this reward to optimize for high information gain, ensuring that clarifications effectively reduce uncertainty and improve task completion within the agent-tool-user environment. We validate our framework within a clarification-enhanced $τ$-Bench environment, conducting cross-agent evaluations across five heterogeneous backbones. Empirical results demonstrate that our method consistently improves the success rate by 3.7\% over the no-clarification baseline, while adding only 0.3 total interaction steps on average. --- ### How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes Authors: Aarav Bedi Published: 2026-06-02 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2606.03134v1 Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are usually produced by the robot's own success check. A particularly damaging error is the false success: an episode the robot logs as a success when the task outcome was actually wrong. We ask a narrow but practical question about these episodes. Once an episode has already been flagged as a success, how much of the information needed to overturn that label is present in proprioception, and how much requires vision? We build a simulated testbed on two bimanual ALOHA tasks, induce failures through environment perturbations rather than label edits, label every episode by privileged simulator state that the detector never sees, and keep only episodes the robot flagged as successful. We then compare detectors restricted to proprioception against a vision-based detector. We find that recoverability spans a wide range: in cube transfer the false successes are almost fully recoverable from joint data alone, while in peg insertion proprioception recovers only part of them and a vision detector closes most of the gap. We also show that the proprioceptive separability we measure rests on velocity differences far below any realistic sensor noise floor, so it is best read as an optimistic upper bound that a noiseless simulator inflates. We release the generation and evaluation pipeline. --- ### DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling Authors: Chang Liu, Shuyi Zhang, Changsheng Ma, Yongfeng Tao, Minqiang Yang, Bin Hu Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03132v1 Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still formulate counseling as a local response generation problem, focusing on empathetic replies within short, text-only, or single-session interactions. We argue that this formulation fundamentally mismatches the nature of real psychotherapy. In clinical CBT, therapy is a longitudinal process in which therapists continuously infer, update, and intervene on evolving therapeutic states across sessions. Realistic CBT further involves multimodal inference and delayed cross-session intervention effects, requiring models to capture longitudinal therapeutic state evolution under partial observability. We propose DMT-CBT, a framework for Dynamic Modeling of evolving Therapeutic states in CBT counseling. DMT-CBT maintains structured therapeutic states across sessions while incorporating multimodal behavioral grounding and tool-augmented intervention to support adaptive therapeutic reasoning. Based on this framework, we construct DMTCorpus, a synthetic multi-session multimodal CBT counseling dataset featuring evolving therapeutic states, image-grounded client behaviors, and cross-session intervention continuity. Experimental results show that DMT-CBT improves counseling fidelity and therapeutic alliance, produces more favorable longitudinal affective trajectories, and preserves therapeutic states more faithfully than post-hoc extraction approaches. --- ### HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models Authors: Shuang Liu, Yuxuan Bo, Qiuyang Zhao, Caiyue Huang, Xiaorong Chen, Yanguang Liu, Mengnan Du Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03131v1 Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking. To evaluate reward-model robustness, we introduce RewardHackBench containing 13 reward-hacking patterns covering real life high-stakes domains and general settings, and we find severe failures on specific subcategories across eight reward models. To mitigate these failures, we propose HARVE, a training-free reward-head editing method for scalar reward models. Instead of fine-tuning the reward model, HARVE identifies a multi-directional hacking subspace from residual stream directions associated with selected hacking subcategories, and removes the component of the reward-head vector aligned with that subspace. This directly reduces the reward head's sensitivity to hacking-related features using only a small set of contrastive gold-hacked examples, without gradient updates or fine-tuning. Comprehensive experiments across eight reward models indicates that \model improves hacking robustness, outperforms fine-tuning baselines, and preserves reward-models' general capability. Further analyses suggest that reward hacking is better captured as a multidimensional residual-space structure than by isolated surface cues. --- ### Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation Authors: Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg, Amabel Gale, Xiaoyu Liu, Pareesa Ameneh Golnari, Shengyu Fu Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03130v1 Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to methods, parameters, variables, and imports that do not exist in the surrounding project. Existing mitigations either require per-language execution sandboxes that do not apply at mid-keystroke or preference-optimisation pipelines that need large human-labelled corpora. We propose an execution-free alternative: use frontier code models to synthesise plausible-but-wrong completions as hard negatives, then leverage the contrast between these synthetic hallucinations and the ground-truth developer edit as a supervised fine-tuning signal. Our pipeline scrapes multilingual FIM contexts from public GitHub across eight languages and asks a panel of three frontier generators to produce one hard negative per context for each of four hallucination types drawn from the Delulu taxonomy, a Docker-verified multilingual FIM hallucination benchmark, yielding a paired chosen/rejected dataset. Fine-tuning Qwen2.5-Coder-7B-Instruct on a 100K-row curated subset lifts Delulu exact match by +18.8 points and edit similarity by +0.22 on every language and every type, while also improving every HumanEval-Infilling split and every SAFIM subset. The same recipe at 3B lifts Delulu by +12.8 EM with a small, characterised general-FIM trade-off. Five-axis ablations (size, type mix, language coverage, base-model family, and a difficulty-aware fool rate) plus a head-to-head SFT vs. DPO/ORPO comparison map which design choices drive the gain. We release the full pipeline source code -- generation, fool-rate LLM judging, curation, and the FIM fine-tuning recipe -- so that the experiments in this paper can be reproduced end-to end on any permissively licensed corpus. --- ### Decoupled Smart Contract Audits: Lightweight LLM Framework via Distillation and Aggregation Authors: Bagus Rakadyanto Oktavianto Putra, Muhamad Risqi Utama Saputra, Widyawan, Guntur Dharma Putra Published: 2026-06-02 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.03128v1 Smart contracts face critical security challenges that require thorough auditing in decentralized web services. While Large Language Models (LLMs) have shown promise in automated vulnerability detection, existing approaches lack severity evaluations with actionable remediation and demand unnecessarily massive computational overhead. In this study, we introduce an efficient end-to-end smart contract security audit framework utilizing lightweight, highly optimized open-source LLMs (0.6B-4B parameters). Our framework decouples comprehensive audit tasks into four interconnected components: vulnerability detection, explanation, severity classification, and remediation recommendation. To maintain high accuracy without massive parameters, we implement Rank-Stabilized Low-Rank Adapters (rsLoRA), knowledge distillation, and a custom Chain-of-Verification (CoVe) aggregation strategy to systematically screen and consolidate multiple draft responses from the model into a highly accurate audit report. Experimental results demonstrate that our lightweight pipeline consistently outperforms state-of-the-art open-source coder dense LLMs (7B to 34B parameters), achieving 98.25% accuracy in vulnerability detection and an alignment score of 0.4375 in generative explanation tasks. Furthermore, our extensive ablation studies empirically validate the superiority of our decoupled audit processes over unified prompting and uncover a novel severity centrality bias, establishing a critical benchmark for future research in LLM-assisted auditing. --- ### Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies Authors: Dhruvi Khandelwal, Anurag Basistha, Ayushi Jolotia, Parikshit Pareek Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03125v1 Deep learning proxies for Alternating Current Optimal Power Flow (ACOPF) lack systematic methods for determining architectural size. This paper conducts a constructive thought experiment to answer a fundamental inquiry: how wide must a neural network be to almost accurately approximate the ACOPF manifold? We introduce a Loss-Guided Neural Densification (LG-ND) algorithm that incrementally discovers necessary capacity by expanding only when the current deep neural network topology fails to improve further. Empirical results across various IEEE systems show that LG-ND achieves performance parity with literature baselines using up to ten times fewer neurons per layer. Such architectural minimalism is critical for the formal verification required in safety-critical grid operations. --- ### TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching Authors: Zhe Li, Jindong Tian, Hao Miao, Zhi Lei, Chenjuan Guo, Bin Yang Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03121v2 Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to the diversity of data sources, time series exhibit diverse temporal dynamics, often accompanied by various irregularities such as missing values and non-uniform sampling frequencies. Such irregularities lead to complex and asynchronous temporal dependencies across channels. Thus, a single model with a fixed patching scheme often fails to adapt well to diverse multivariate time series, hindering accurate forecasting. In this paper, we propose TiWeaver, a unified framework designed to handle temporal dynamics and fine-grained inter-channel dependencies adaptively. Specifically, we introduce a Graph-Guided Adaptive Tokenizer (G$^2$AT) that divides time series into high contextually coherent patches by jointly considering temporal density and representation consistency. In addition, we propose a Fine-grained Asynchronous Dependency Extractor (FADE), which is designed to model fine-grained asynchronous inter-channel dependencies while incorporating long-term historical dependencies. We evaluate TiWeaver on 12 real-world time series datasets, where it achieves state-of-the-art performance, outperforming existing methods up to 25%. These results demonstrate its robustness and effectiveness across diverse domains and data characteristics. --- ### TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching Authors: Zhe Li, Jindong Tian, Hao Miao, Zhi Lei, Chenjuan Guo, Bin Yang Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03121v1 Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to the diversity of data sources, time series exhibit diverse temporal dynamics, often accompanied by various irregularities such as missing values and non-uniform sampling frequencies. Such irregularities lead to complex and asynchronous temporal dependencies across channels. Thus, a single model with a fixed patching scheme often fails to adapt well to diverse multivariate time series, hindering accurate forecasting. In this paper, we propose TiWeaver, a unified framework designed to handle temporal dynamics and fine-grained inter-channel dependencies adaptively. Specifically, we introduce a Graph-Guided Adaptive Tokenizer (G$^2$AT) that divides time series into high contextually coherent patches by jointly considering temporal density and representation consistency. In addition, we propose a Fine-grained Asynchronous Dependency Extractor (FADE), which is designed to model fine-grained asynchronous inter-channel dependencies while incorporating long-term historical dependencies. We evaluate TiWeaver on 12 real-world time series datasets, where it achieves state-of-the-art performance, outperforming existing methods up to 25%. These results demonstrate its robustness and effectiveness across diverse domains and data characteristics. --- ### KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis Authors: Vivekjyoti Banerjee, Abhay Yadav, Rama Chellappa, Aniket Roy Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03120v1 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiable rasterization. However, standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales. This leads to oversmoothing and structural artifacts, particularly in sparse-view settings where supervision is limited. We propose KC-3DGS, which augments 3DGS training with wavelet-domain supervision based on natural image statistics. Our method combines three components: (1) a multi-scale wavelet coefficient alignment loss that explicitly penalizes missing high-frequency detail, (2) a supervised kurtosis concentration loss that encourages rendered images to match the heavy-tailed frequency statistics of ground-truth images, and (3) a cross-band covariance penalty that promotes frequency specialization. We provide theoretical analysis showing that pixel-space losses admit a family of indistinguishable perturbations under wavelet redistribution, and that our joint objective excludes degenerate solutions. Experiments across MipNeRF360, Tanks&Temples, MVImgNet, DeepBlending, and WRIVA-ULTRRA demonstrate consistent improvements in perceptual quality. On the challenging WRIVA-ULTRRA outdoor dataset, KC-3DGS achieves a 9.48% improvement in DreamSim while also improving PSNR, SSIM, and LPIPS. In sparse-view settings with only 12 training images, our method improves PSNR by up to 0.5 dB on MipNeRF360 while maintaining perceptual quality. The approach integrates seamlessly into existing 3DGS pipelines as a plug-and-play regularization strategy. --- ### GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance Authors: Zehua Chen, Yucheng Yang, Binjie Yuan, Kaiwen Zheng, Jun S. Liu, Jun Zhu Published: 2026-06-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.03119v1 Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently, bridge models have introduced a data-to-data generative process that can exploit an instructive clean prior. In this work, inspired by previous methods creating quality difference between denoising results as guidance, we propose a training-free bridge guidance method, termed Prior Guidance (PG). Specifically, we introduce a weak prior, which is unseen during bridge pre-training, hindering prior exploitation and thereby degrading denoising result. Then, we contrast it with the seen prior to highlight and enhance prior exploitation via a scaling factor. Moreover, we analyze the underlying mechanism of prior exploitation in the bridge process and design frequency-modulated prior guidance (FMPG), which tailors the guidance scale to low- and high-frequency bands coherent with bridge generative dynamics. To address prior exploitation in image in-painting, we develop a cascaded framework, CFG-FMPG, which first generates a noisy hidden representation via CFG and then exploits it as a generative prior with FMPG, fulfilling their complementary strengths without compromising inference efficiency. Experiments demonstrate that our PG methods consistently improve pre-trained bridge models across diverse image translation tasks. --- ### Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning Authors: Jacob Lavoie, Marwan Besrour, William Lemaire, Jean Rouat, Réjean Fontaine, Eric Plourde Published: 2026-06-02 Categories: cs.LG, cs.CV, q-bio.NC arXiv: https://arxiv.org/abs/2606.03118v1 Objective: Diseases such as age-related macular degeneration and retinitis pigmentosa cause the degradation of the photoreceptor layer. One approach to restore vision is to electrically stimulate the surviving retinal ganglion cells with a microelectrode array such as epiretinal implants. Epiretinal implants are known to generate visible anisotropic shapes elongated along the axon fascicles of neighboring retinal ganglion cells. Recent work has demonstrated that to obtain isotropic pixel-like shapes, it is possible to map axon fascicles and avoid stimulating them by inactivating electrodes or lowering stimulation current levels. Avoiding axon fascicle stimulation aims to remove brushstroke-like shapes in favor of a more reduced set of pixel-like shapes. Approach: In this study, we propose the use of isotropic and anisotropic shapes to render intelligible images on the retina of a virtual patient in a reinforcement learning environment named rlretina. The environment formalizes the task as using brushstrokes in a stroke-based rendering task. Main Results: We train a deep reinforcement learning agent that learns to assemble isotropic and anisotropic shapes to form an image. We investigate which error-based or perception-based metrics is adequate to reward the agent. The agent is trained in a model-based data generation fashion using the psychophysically validated axon map model to render images as perceived by different virtual patients. We show that the agent can generate more intelligible images compared to the naive method in different virtual patients. Significance: This work shares a new way to address epiretinal stimulation that constitutes a first step towards improving visual acuity in artificially-restored vision using anisotropic phosphenes. --- ### AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following Authors: Haitao Li, Tian Tan, Yuguang Yang, Shan Yang, Xie Chen Published: 2026-06-02 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.03116v2 The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation. Current automated evaluation methods heavily rely on holistic scoring from general-purpose large language models, which struggle to decouple complex instructions, lack interpretability, and fail to capture fine-grained attribute mismatches. To address this, we introduce a novel dynamic rubric-based evaluation paradigm that adaptively decomposes complex audio captions into a variable number of independent, verifiable binary rubric items. To rigorously benchmark this capability, we propose the AnyAudio-Judge Bench, a comprehensive, bilingual benchmark comprising 7,920 meticulously curated samples across four diverse audio domains (speech, sound, music, and mixed), featuring deliberately constructed hard negatives. Furthermore, we construct a large-scale corpus of 105K samples with explicit Chain-of-Thought (CoT) rationales to train our dedicated evaluator, the AnyAudio-Judge model. By employing a training pipeline that combines Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), our model successfully aligns its reasoning paths with the rubric-based scoring mechanism. Extensive experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines, but also provides precise and interpretable reward signals that substantially improve instruction alignment in downstream reinforcement learning for audio generation. --- ### AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following Authors: Haitao Li, Tian Tan, Yuguang Yang, Shan Yang, Xie Chen Published: 2026-06-02 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2606.03116v1 The rapid advancement of instruction-guided audio generation has highlighted the critical need for robust alignment evaluation. Current automated evaluation methods heavily rely on holistic scoring from general-purpose large language models, which struggle to decouple complex instructions, lack interpretability, and fail to capture fine-grained attribute mismatches. To address this, we introduce a novel dynamic rubric-based evaluation paradigm that adaptively decomposes complex audio captions into a variable number of independent, verifiable binary rubric items. To rigorously benchmark this capability, we propose the AnyAudio-Judge Bench, a comprehensive, bilingual benchmark comprising 7,920 meticulously curated samples across four diverse audio domains (speech, sound, music, and mixed), featuring deliberately constructed hard negatives. Furthermore, we construct a large-scale corpus of 105K samples with explicit Chain-of-Thought (CoT) rationales to train our dedicated evaluator, the AnyAudio-Judge model. By employing a training pipeline that combines Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO), our model successfully aligns its reasoning paths with the rubric-based scoring mechanism. Extensive experiments demonstrate that AnyAudio-Judge not only significantly enhances zero-shot alignment detection compared to state-of-the-art baselines, but also provides precise and interpretable reward signals that substantially improve instruction alignment in downstream reinforcement learning for audio generation. --- ### FAF-CD: Frequency-Aware Fusion for Change Detection under Imperfect Multimodal Remote Sensing Authors: Yufan Wang, Sokratis Makrogiannis, Chandra Kambhamettu Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03114v1 Remote sensing change detection for real-world monitoring often relies on imperfect heterogeneous observations, where pre- and post-event images may be asynchronous, cross-sensor, or affected by illumination, seasonal, and modality shifts. This setting is especially challenging for EO-SAR disaster mapping, where nuisance variation can resemble structural damage. We propose FAF-CD, a frequency-aware hybrid framework with a DINOv3-pretrained ConvNeXt encoder and a linear-complexity VMamba-based decoder. Its rectification-aware tri-branch fusion module combines deformable spatial alignment with Fourier and Haar-wavelet comparisons, using adaptive gating to aggregate complementary cues across scales. On BRIGHT validation, a matched heterogeneous EO-SAR adaptation improves clean and perturbed tc-mIoU/tc-mAP over NeXt2Former-CD. FAF-CD also generalizes to binary optical CD, achieving 0.924 cF1 on LEVIR-CD and 0.955 cF1 on WHU-CD, and obtains the best average perturbed cIoU/cF1 on both binary datasets among M-CD and NeXt2Former-CD under pseudo-change-aligned stress tests. It further reduces cost by approximately 24 GFLOPs relative to NeXt2Former-CD while maintaining or improving accuracy. --- ### Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Authors: Yanyu Zhu, Hoilam Pao, Niu Hu, Wei Guo, Shaoxiong Zhan, Boyu Lai, Zitai Wang, Yongqin Zeng, Hai-Tao Zheng Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03113v1 Large Language Models suffer from slow autoregressive inference. While self-speculative decoding accelerates this process, its efficiency is hampered by static configurations like fixed exit layers and speculation lengths. We reframe this optimization as a \textbf{Markov Decision Process} and propose \textbf{LEDE}, a framework that uses offline reinforcement learning. LEDE learns a policy to dynamically select the optimal exit layer and speculation length based on the local context of the generated sequence at each step, balancing computational cost and draft quality. Comprehensive evaluations on Llama-2 and Llama-3 models show LEDE achieves up to a $2.0\times$$\sim$$2.7\times$ speedup over autoregressive decoding and and provides an additional 17\% speedup over the static speculative baselines. --- ### Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data Authors: Jingzhe Kang Published: 2026-06-02 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2606.03112v1 With the increasing scale and number of wind farms, wind turbines' daily operation and maintenance costs are increasing. To reduce operation and maintenance costs and enhance the reliability of wind turbine and system operation data before reaching catastrophic failures, monitoring the operating status of the equipment and detecting failures at an early stage is crucial. It is of great practical significance to utilize the working condition data for abnormal assessment of the operating status of wind turbines to realize abnormal monitoring of the operating status of wind turbines. However, the existing anomaly detection methods can neither perform effective relational modeling in data filled with a large amount of redundant information nor reasonably utilize the valuable anomaly data. For this reason, this paper proposes an anomaly detection model that fuses a Transformer and a generative adversarial network. Firstly, it reduces the leakage detection rate of minor deviation anomalies by amplifying the reconstruction error. Secondly, it uses autoregressive inference to extract multimodal features to enhance the stability and generalization ability of training. Finally, the temporal feature extraction module is constructed to promote the interactive learning between features of different time scales and effectively reduce the time redundancy. The results of multiple sets of experiments conducted on real WTG datasets show that TransGAN-WT achieves an average F1 score of 96.10% across multiple wind turbine datasets, which is 5.84% and 2.89% higher than several other state-of-the-art baseline methods. It also realizes a false positive rate (FPR) of 0.06%, and is verified by the Wilcoxon signed-rank test to have achieved a statistically significant performance enhancement compared to the state-of-the-art baseline methods, effectively ensuring the stable operation of wind turbines. --- ### Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method Authors: Yan Zeng, Masanori Suganuma, Takayuki Okatani Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.03111v1 This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing methods often struggle with accuracy in this task. We propose a novel hybrid approach that combines direct inversion via gradient descent for the first step, followed by a fixed-point method for subsequent steps. Empirical evaluations across three datasets demonstrate that our method significantly improves the prediction of initial latent variables while achieving superior reconstruction accuracy. Additionally, we introduce a new evaluation, called the self-interpolation test, which assesses the quality of images generated from interpolated points between the true and predicted latent maps, offering deeper insights into performance. Our results reveal that while existing methods perform reasonably well in reconstruction, they consistently fail to accurately predict the initial latent variables, resulting in poor performance on the self-interpolation test. In contrast, our method outperforms all others across all metrics, providing valuable insights into diffusion models and enhancing their applications in image generation and editing. --- ### Coherence Maximization Improves Pluralistic Alignment Authors: Taslim Mahbub, Yiding Pei, Shi Feng Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03110v2 Aligning AI systems with diverse human values requires value specifications grounded in concrete examples, but generating such examples without extensive human supervision remains an open challenge. We investigate what makes these examples effective, using Internal Coherence Maximization (ICM) -- which infers labels by maximizing their mutual predictability -- to generate persona-specific examples that steer a model toward a target group's values, without human supervision. Across four benchmarks spanning classification, preference, and open-ended generation, ICM-inferred in-context examples match the performance of gold labels. Crucially, coherence matters beyond individual label accuracy: with accuracy held constant, more coherent examples generalize substantially better than incoherent ones. For personas underrepresented in pretraining data, targeted human feedback on the questions where the model is least certain about a persona's values yields better generalization than the same number of labels on arbitrary questions. These results identify coherence as a key design principle for scalable value specification, leveraging the diverse human perspectives already encoded in pretrained language models. --- ### EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning Authors: Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03108v2 Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them. --- ### DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration Authors: Wenkai Wang, Tao Xiong, Jingchen Ni, Yunpeng Bao, Xiyun Li, Tianqi Liu, Hongcan Guo, Zilong Huang, Shengyu Zhang Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03103v1 Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses. Yet existing desktop GUI benchmarks mostly reduce this setting to short, simplified tasks with all user instructions provided upfront. To address this issue, we introduce DeskCraft, a desktop GUI benchmark targeting long horizon creative and engineering workflows and proactive human-agent collaboration. DeskCraft organizes tasks into a multilevel difficulty taxonomy, with long horizon tasks requiring over 50 execution steps, and covers professional creative software across design, video, audio, and 3D creation. Furthermore, DeskCraft formalizes human-agent collaboration into an interaction protocol covering mid-turn and post-turn exchanges. Mid-turn interaction captures both agent-initiated clarification under uncertainty and user-initiated interruption during execution, while post-turn interaction accommodates user-driven feedback after the agent signals completion, together spanning the full space of realistic collaboration patterns. We evaluate 18 proprietary and open source agents on 538 tasks and find that GPT-5.4 reaches 31.6% on standard tasks and 27.6% on interactive tasks. Further analyses reveal persistent failures in long horizon workflow delivery and proactive clarification. We will open-source all evaluation codes, tasks, and data at https://github.com/mrwwk/DeskCraft. --- ### Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling Authors: Runpeng Dai, Tong Zheng, Rui Liu, Chengsong Huang, Hongtu Zhu Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03102v1 Test-time scaling improves the reasoning performance of large language models but incurs substantial cost in both total computation and latency. Existing adaptive sampling methods partially mitigate this issue by dynamically deciding when to stop sampling, yet they typically rely on heuristic rules or rely on distribution assumptions. In this work, we formulate adaptive sampling as a Markov decision process (MDP). We train a lightweight sampling controller with reinforcement learning (RL) to jointly balance answer correctness, latency, and computation cost. At each round, the controller decides to stop sampling or to acquire additional samples. Our method is lightweight which only relies on statistics of final answers, and can be trained and deployed on CPU. We further show that the resulting framework admits an interpretation as the Lagrangian relaxation of a constrained optimization problem with explicit budget constraints. Experiments against strong baselines such as ASC and ESC show that our method achieves improved trade-offs among answer correctness, sampling rounds, and total samples required. --- ### Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation Authors: Dongsheng Wang, Dawei Su, Hui Huang Published: 2026-06-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.03100v2 Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities. Typically, multiple 2D views are sampled from a 3D point cloud and fed into pre-trained VLMs to answer a given question. This paradigm highlights the critical role of input context quality and raises the challenge of retaining as many task-relevant 3D details as possible under a limited input budget. We propose \texttt{KeyVT}, a hierarchical approach for input context collection at both the view and token levels. Specifically, we combine pixel features with camera parameters and assess view importance based on both semantic content and geometric position, resulting in spatially consistent and task-relevant views. Furthermore, we address redundancy among patches across selected views by identifying representative tokens under the optimal transport (OT) framework, where view tokens and key tokens are formulated as two discrete distributions in the embedding space. These key tokens are expected to cover all view features by minimizing the OT distance. We evaluate our framework on three widely used benchmarks, demonstrating significant improvements over existing tuning-free methods and performance comparable to training-based approaches. --- ### PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Search Authors: Kailin Lyu, Zhiqiang Yuan, Jianwei He, Qiwei Yan, Xuanbo Su, Nanxing Hu, Yang Liu, Ce Hao, Shengqian Qin, Lianyu Hu, Jinchao Zhang, Jie Zhou Published: 2026-06-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2606.03099v1 Deep Image Search requires multi-step reasoning over rich contextual cues, such as time, location, and event relations. However, most existing LLM-based agents are stateless and reactive, lacking persistent memory to maintain long-horizon context or transfer experience across tasks, which often leads to execution drift and experience isolation. To address these limitations, we propose PhotoCraft, a training-free, hierarchical memory system for photo-search agents. Inspired by human cognition, PhotoCraft equips MLLMs with working, episodic, and semantic memory, which are dynamically invoked during reasoning to preserve logical consistency and knowledge transferability throughout multi-step reasoning and answer generation. Extensive experiments on DISBench demonstrate that PhotoCraft consistently improves context-aware retrieval across diverse MLLM backbones, achieving gains of up to 18.5\% and effectively mitigating key bottlenecks in memoryless deep image search, offering a practical path toward reliable and generalizable multimodal search agents. --- ### From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting Authors: Mingyang Liu, Qingcan Kang, Yuke Wang, Shixiong Kai, Kaichao Liang, Hui-Ling Zhen, Tao Zhong, Mingxuan Yuan, Linqi Song Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03097v1 Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens. --- ### Can Factual Opinions Be Edited (Manipulated) in Large Language Models? Authors: Yuanpu Cao, Ziyi Yin, Fenglong Ma, Jinghui Chen Published: 2026-06-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.03096v2 Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods primarily target atomic facts, overlooking the significant risks associated with manipulating factual opinions, e.g., documented stances of public figures on societal issues. Such manipulation could reshape public images, influence elections, and alter societal views. To systematically assess this threat, we introduce the Factual Opinion Editing with Evidence (FOE) benchmark, which encompasses 261 public figures, 19 issue categories, and 2,178 complete opinion records. Our evaluations demonstrate that current editing techniques struggle significantly with factual opinions, often achieving only superficial changes while failing to preserve consistency between the edited opinion and the supporting evidence generated by the model. To address this limitation, we further propose a simple yet effective Self-Generated Evidence-Aligned method that achieves opinion-evidence alignment without relying on explicit instructions. Together, our benchmark and method provide a foundation for understanding the emerging security implications of factual opinion editing in LLMs. --- ### FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data Authors: Pengyu Chen, Shaowei Li, Kai Wang, Yunsheng Yuan, Kai Han, Jun Luo, Feng Li Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.03094v1 Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasoning. While group relative policy optimization (GRPO) offers superior scalability by eliminating the critic network, deploying it on a central infrastructure entails collecting a large volume of data from distributed owners, which poses significant privacy risks. To address these concerns, we introduce federated GRPO (FGRPO), a framework designed to decentralize the fine-tuning of reasoning models across heterogeneous data owners. To effectively mitigate the instability caused by divergent reward scales across heterogeneous tasks, FGRPO incorporates an adaptive aggregation mechanism based on relative performance gain. By characterizing each client's improvement relative to its personalized historical baseline, the framework dynamically prioritizes effective learning trajectories regardless of local task difficulty. FGRPO ensures robust convergence on non-IID data while preserving data privacy. --- ### Decomposing how prompting steers behavior Authors: Fan L. Cheng, Nikolaus Kriegeskorte Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03093v1 Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates, but it remains unclear how instruction changes reshape internal representations to produce behavior. We introduce a nested geometric decomposition framework that treats prompting as a transformation of the representational geometry of the content following the prompt. For each prompt pair, we align representations of the same stimuli under two prompts using increasingly expressive stimulus-invariant maps: translation, rigid transformation with uniform scaling, sequential axis scaling, affine transformation, and nonlinear transformation. We then causally test each map by replacing a single layer's prompt-A hidden state for held-out stimuli with its mapped counterpart and measuring recovery of prompt-B representational geometry and behavior. Across three LLMs, three VLMs, and six text or image datasets spanning style, emotion, scene content, and number, prompts consistently reshape representations toward the instructed task structure. Cross-validated variance decomposition shows that much prompt-induced activation change is captured by shape-preserving maps, especially translation and rigid transformation with uniform scaling, while tier profiles reveal model- and task-specific routing strategies across layers. Crucially, although translation and rigid tiers already improve behavioral agreement, affine transformation is the first tier to nearly recover target-prompt task geometry and yields corresponding behavioral gains. This suggests that cross-dimensional linear mixing is a key mechanism by which prompts reorganize representations toward instructed task structure. Our framework decomposes prompt-induced representational change into interpretable geometric components and reveals how models route task-relevant structure to produce prompt-driven behavior. --- ### The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs Authors: Xu Wan, Speed Zhu, Jianwei Cai, Guang Chen, XiMing Huang, Wiggin Zhou, Mingyang Sun Published: 2026-06-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.03092v2 Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for Reasoning (CLEAR). It performs rational abandonment and reallocates resources from insolvent queries to solvable queries near their emergence thresholds. Extensive experiments on several reasoning tasks with different traffic streams demonstrate that CLEAR significantly improves the Pareto frontier of total token cost versus mean accuracy. In resource-scarce regimes, CLEAR achieves up to a 3x improvement in global accuracy compared to uniform allocation. ---