Artificial Intelligence · Cross-listed from cs.CV
OneWorld: Learning Consistent Physics Across Actions in World Models
Ke He, Yichen Ding and Bin Yang
Action-conditioned
video world models aim to predict scene
evolution under different actions, a capability that is essential for reliable planning, decision-making, and interaction in dynamic environments. However, futures generated independently from the same initial scene may each appear plausible while implying incompatible physical properties, such as friction or mass. This inconsistency can lead to contradictory predictions across interventions, making it difficult for the model to maintain a coherent understanding of the underlying world and limiting its reliability for planning and decision-making. To address these issues, we propose OneWorld, a shared-mechanism counterfactual generation framework that jointly models multiple action-conditioned futures under a common latent physical mechanism. A physical mechanism interpreter first infers a distribution over latent mechanisms from each action-outcome branch. These distributions are then aggregated into shared-world evidence, which captures whether the branches admit a common physical explanation while accounting for uncertainty in less informative branches. This evidence constrains flow training and guides sampling, encouraging consistency in the underlying physical mechanism while preserving the distinct outcomes induced by different actions. We further introduce a multi-intervention evaluation protocol in controlled environments, following the interaction settings of ACWM-Phys, to assess whether generated futures can be jointly explained by the same physical parameters, alongside standard measures of single-rollout prediction quality. Experiments in these environments show that OneWorld improves cross-intervention physical consistency while maintaining competitive single-rollout prediction quality.
Read the full abstract ▾
Artificial Intelligence
LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
Jiaqi Zhu, Naili Xing, Hexiang Pan et al. (+4 more)
Long-form technical text generation underpins knowledge-intensive workflows, yet remains challenging for large
language models (LLMs) due to the need for globally consistent logical structuring and faithful technical
reasoning beyond local coherence. Patent drafting is a canonical instance of this challenge, demanding holistic generation of a legally compliant and technically exhaustive document through sustained multi-expert collaboration. Existing approaches often focus on partial section generation or rely on manually crafted outlines, limiting scalable automation in realistic settings. In this work, we propose LogicTree-RAG, a logic tree-guided
retrieval-augmented generation framework that induces a hierarchical logic tree as a global organizational backbone to organize and ground technical disclosures, without relying on expert-defined drafting priors. Each node in the logic tree represents a technical element and is constructed through evidence-guided recursive generation. A hybrid traversal mechanism then maps the logic tree into patent sections, enabling controllable and section-balanced generation. Extensive experiments show that LogicTree-RAG consistently improves content quality and
language conformity over strong LLM-based baselines and achieves longer structured generation with high
token efficiency, demonstrating the effectiveness of logic-centric generation for complex technical document drafting.
Read the full abstract ▾
All authors Jiaqi Zhu, Naili Xing, Hexiang Pan, Haotian Gao, Jianwei Yin, Xiaokui Xiao, Beng Chin Ooi
Artificial Intelligence · Cross-listed from cs.CV
Spackle: Completing Large View Single Image NVS with Adaptive Gaussians
Xuanzhi Liu, Yuhe Zhou, Xinyi Wu et al. (+4 more)
Single-image novel view synthesis (NVS) enables photorealistic rendering of un- observed viewpoints from a single input. Practical NVS systems require two key capabilities: robust reconstruction of occluded regions and high inference effi- ciency. While hybrid decoupled frameworks combining feedforward 3D Gaussian Splatting (3DGS) and
diffusion models show promise for large-view-deviation NVS, they suffer from capacity competition: a fixed number of Gaussians forces resource shifts from visible to newly disoccluded areas, degrading original scene fidelity when the target view deviates significantly from the input. To address this, we propose Spackle, a lightweight residual learning framework that mit- igates capacity competition without sacrificing efficiency. Spackle operates in three stages: predicting base 3DGS attributes from given views, automatically identifying poorly reconstructed regions, and learning a residual 3DGS optimized exclusively for these areas. At inference, we combine the baseline and aug- mented Gaussians for NVS. We conduct comprehensive experiments and show that Spackle achieves state-of-the-art performance on large-view-deviation cases.
Read the full abstract ▾
All authors Xuanzhi Liu, Yuhe Zhou, Xinyi Wu, Zhenyao Wu, Jinghao Chen, Ruize Han, Song Wang
Artificial Intelligence
Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms
Zhenhao Fu, Ruipeng Xu and Qibing Ren
Individually protective decisions can produce avoidable collective failures. As large
language model (LLM)
agents take on greater roles in financial decision-making, financial AI safety must therefore be considered not only at the level of individual
agents, but also at the level of the systems they jointly create. We study this problem with FRAIL, a controlled experimental framework that places LLM
agents in three dynamic financial environments—bank runs, debt rollover, and reward crowdfunding—where
agents' decisions reshape the financial conditions faced by others. Across seven leading LLMs, we find widespread collective fragility even when no
agent is instructed to destabilize the system: 77% of baseline bank-run episodes and 83% of debt-rollover episodes end in failure. We then compare three interaction mechanisms based on compensated commitments, centralized commitment agreements, and participant-led coalitions. All three improve aggregate outcomes, but no single mechanism performs best across all financial structures. Across mechanisms, successful stabilization shares a common temporal pattern: broad commitment forms early, before defensive behavior becomes self-reinforcing. Our findings show that individually capable
agents do not automatically form safe financial systems, highlighting system-level evaluation and interaction design as central problems for financial AI safety. Code is available at https://anonymous.4open.science/r/FinFrail-CF26.
Read the full abstract ▾
Artificial Intelligence
MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory
De Jiang, Shuo Zhang, Weiwei Liao et al. (+4 more)
Cognitive behavioral therapy (CBT) is an evidence-based first-line treatment for depression, yet its scale is constrained by the time clinicians spend on pre-session preparation, post-session documentation, and longitudinal cognitive-pathology tracking. We present a clinician-facing AI decision-support system that combines a multi-
agent CBT framework (MACBT) with a CBT-specific longitudinal
memory module (CD
Memory). MACBT encodes the five-stage CBT workflow (assessment, Socratic questioning, cognitive restructuring, behavioral experiments, and treatment monitoring) into five collaborative
agents. CD
Memory tracks cognitive-distortion type, frequency, severity, and restructuring efficacy across sessions to generate pre-session pathology reports and intervention-priority recommendations. We construct a Chinese CBT dialogue corpus via dual-role large
language model simulation and train a Qwen3-14B backbone with supervised fine-tuning and direct preference optimization. Evaluation with GPT-4 judges shows MACBT outperforms MeChat, SoulChat, PsyChat, and CPsyCounX in professionalism (2.62) and clinical authenticity (2.25). The full
memory-augmented system further improves session quality by 12.6% and achieves a longitudinal mean of 2.29 on cross-session continuity, intervention progression, and personalization.
Read the full abstract ▾
All authors De Jiang, Shuo Zhang, Weiwei Liao, Jianying Zhang, Chuanhui Yu, Hongen Liao, Kehong Yuan
Artificial Intelligence
Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni et al. (+5 more)
Improving
reasoning abilities in Large
Language Models (LLMs) requires high-quality data that exposes difficult decisions, competing alternatives, and their consequences. Data scarcity is driven by the low quality of synthetic data and the cost of human labeling. We introduce Self-Play Search
Distillation (SPSD), a framework for generating superhuman synthetic data via self-play of MuZero-like networks trained on board games. SPSD uses executable environments to turn search into structured
reasoning problems. At each state, the expert identifies a preferred decision, plausible alternatives, plausible opponent replies, and value estimates. By converting the self-play search records into superhuman chains-of-thought, we train LLMs with environment-grounded supervision. Although trained only on self-play search records, SPSD transfers to unseen mathematics. On Qwen3-4B-Base, it raises the mean over six mathematics
benchmarks from 24.1 to 36.6 while increasing the held-out-game win rate from 15% to 45%. SPSD offers an annotation-efficient way to create high-quality synthetic data for improving LLM performance in
reasoning tasks.
Read the full abstract ▾
All authors Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni, Luca Ragazzi, Gianluca Moro, Pavlos Vougiouklis, Jeff Z. Pan, Pasquale Minervini
Artificial Intelligence · Cross-listed from cs.CL
Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models
Bing Wang, Changchun Li, Xin-Qiang Cai et al. (+4 more)
Continual fine-tuning is essential for large
language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from catastrophic forgetting, particularly the performance degradation of previous tasks and LLMs' general-purpose knowledge. Although existing methods, such as orthogonal gradient projection, mitigate the forgetting across various fine-tuning tasks, they fundamentally fail to preserve pre-training LLMs' inherent general-purpose knowledge because the original data and gradients of off-the-shelf pre-training LLMs required by these methods are strictly unknown and highly diverse. To bridge this critical gap, we propose EoupCT, a novel framework designed to Estimate and Orthogonalize Unknown Pre-training gradients for Continual LLM fine-Tuning. Specifically, EoupCT estimates pre-training gradients by dynamically generating pseudo data that is most susceptible to forgetting for new tasks through a learnable soft
prompt equipped with Gumbel-Softmax relaxation. Furthermore, we formulate a multi-objective optimization problem and introduce a first-order efficient Pareto optimizer that jointly optimizes LLM parameters and the soft
prompt, rigorously enforcing orthogonality between new task updates and the estimated pre-training gradients. Extensive experiments across multiple LLMs demonstrate that EoupCT effectively preserves both task-specific proficiency and inherent general-purpose knowledge, successfully mitigating the catastrophic forgetting.
Read the full abstract ▾
All authors Bing Wang, Changchun Li, Xin-Qiang Cai, Lin Yuanbo Wu, Ximing Li, Gang Niu, Masashi Sugiyama
Artificial Intelligence · Cross-listed from cs.CV
UltraG-Bench: A Multi-task Benchmark for assessing Large Vision-Language Models on Pixel-level Evidence Grounding in Ultrasound
Quanhao Zhu, Bo Xu, Rui Lin et al. (+7 more)
Ultrasound is one of the most widely used medical imaging modalities, and recent large
vision-
language models(VLMs) have shown increasing capabilities in ultrasound image understanding. However, these models fail to provide pixel-level visual evidence aligned with their semantic predictions, and their fine-grained grounding capability in ultrasound remains largely unclear. We introduce UltraG-Bench, a large-scale multi-task
benchmark for evaluating pixel-level evidence grounding in ultrasound. UltraG-Bench is built by annotating 40 public ultrasound
segmentation datasets spanning 13 anatomical categories, and comprises three progressive tasks: instruction-guided
segmentation, evidence-grounded VQA, and evidence-grounded report generation, with 331125, 666779, and 138832 annotations, respectively. Comprehensive evaluation of 14 state-of-the-art models reveals a substantial gap between semantic understanding and fine-grained pixel-level localization. We further propose UltraG-
Agent, which combines the semantic
reasoning capabilities of a VLM with the ultrasound-specific
segmentation capability of UltraSAM3. Experiments show that UltraG-
Agent substantially improves both semantic prediction and pixel-level visual grounding. Our
dataset and code are available at https://github.com/zhuqh19/UltraG-Bench.
Read the full abstract ▾
All authors Quanhao Zhu, Bo Xu, Rui Lin, Chenyuan Wang, Yu Shao, Boling Zhu, Jiuyan Sun, Liang Zhao, Hongfei Lin, Feng Xia
Artificial Intelligence
JevSoup: System-One Routing for Training-Free LoRA Composition
Xiuying Wang, Jiahua Cheng, Shuotian Li et al. (+4 more)
Building adaptable AI systems requires effective coordination of specialized capabilities across diverse tasks. Low-rank adaptation (LoRA) enables modular expertise, but existing routing approaches may require auxiliary data, additional training, or autoregressive decoding. We propose JevSoup, a training-free framework separating System One expert routing from System Two execution. Using only the input and expert descriptions, Jev selects two experts through structured probabilities. JevSoup retains the leading expert's update, projects the second onto the orthogonal complement of the first update's row space, and combines them with equal weights. Across 14 PorTAL tasks and three Qwen3 scales, JepSoup achieves absolute gains of up to 1.19% in task-macro and 1.21% in sample-micro accuracy over the strongest evaluated external baselines. Our code is available at https://github.com/Leowang980/JevSoup.
Read the full abstract ▾
All authors Xiuying Wang, Jiahua Cheng, Shuotian Li, Yufan Cheng, Bowen Deng, Zhexuan Bai, Yichen Li
Artificial Intelligence · Cross-listed from cs.LG
Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations
Marcin Kostrzewa and Maciej Zięba
Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what the change is. A small perturbation of the parameters, retraining on new data, and a new architecture are different events, and each existing method is evaluated against the one it was built for. Reported robustness scores, therefore, answer different questions and cannot be compared. We propose a unified cross-family evaluation protocol that holds factual instances and generated counterfactuals fixed while testing every method against the same eight types of model change. The
benchmark compares six robust methods and two standard baselines on four tabular
datasets. It characterizes every changed classifier through its outputs and reports empirical robustness together with coverage, base validity, and proximity. We find that relative performance and failure modes vary across change families. Bounded parameter perturbations change 0.95% of test predictions on average, compared with 4.9% for bootstrap retraining. Methods with guarantees for these perturbations do not necessarily transfer to other changes. RobX transfers most consistently in our experiments, although greater stability can require larger interventions. We argue that robust CFE methods should be evaluated through a common protocol that specifies the model changes, measures their realized behavioral magnitude, and keeps generation performance separate from robustness.
Read the full abstract ▾
Artificial Intelligence
Training Graph Foundation Models on The Web Graph
Ryoma Sato
We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, without additional training, (iii) has in-context learning capabilities, and (iv) does not rely on pretrained LLMs. In particular, existing graph foundation models often require training additional classification heads or feature projectors to accommodate new graphs or new labels, whereas Acacia does not. Moreover, existing graph foundation models often gain their capabilities by being stitched together with pretrained LLMs, whereas Acacia is trained from scratch using only the Common Crawl web graph. This is also an important result because it provides evidence that graph models can acquire emergent capabilities from scratch like LLMs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.SP
Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC
Muhammad Abubakar Rashid, Muhammad Hannan Akram, Haejoon Jung et al. (+1 more)
Semantic communication (SemCom) and integrated sensing and communication (
ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied semantic technology to either the communication module or the sensing module of
ISAC. In this work, we propose SemISAC, which performs both SemCom and semantic sensing within a single dual-function waveform. SemISAC uses a joint semantic encoder that extracts task-specific information for both communication and sensing. We evaluate SemISAC in a vehicular scenario in which vehicles share pixel-wise
segmentation of the road environment and, through sensing, classify surrounding objects and estimate their ranges. On the transmitter side, a deep learning encoder converts the input road-scene image into semantic symbols and places them on the data
cells of an OFDM grid, while the remaining
cells serve as pilots for channel state information estimation and sensing. The pilot configuration is adaptively optimized based on the channel conditions to balance communication and sensing requirements. At the receiver, a deep learning model reconstructs the
segmentation from the received waveform, while the transmitting vehicle captures the reflected waveforms from surrounding objects and uses task-specific deep learning decoders for target recognition and range estimation. Simulation results show that SemISAC achieves a
segmentation accuracy close to that of the dedicated SemCom module while outperforming both conventional and semantic baselines in target recognition and range estimation.
Read the full abstract ▾
All authors Muhammad Abubakar Rashid, Muhammad Hannan Akram, Haejoon Jung, Syed Ali Hassan
Artificial Intelligence
From Tapping to Hopping: Augmenting Mobile GUI Agents with App-Native Deeplinks
Yuchen Sun, Chenglin Cai, Gongjie Zhang et al. (+8 more)
Mobile GUI
agents complete tasks using GUI actions like taps and swipes. These actions are broadly applicable across applications, but reaching a
navigation interface. A single deeplink call can replace a sequence of screen-by-screen GUI actions. We therefore introduce hybrid interaction, using deeplinks for direct
navigation and GUI actions for other on-screen operations and fallback. To enable this, we discover candidate deeplinks through static analysis, validate them on real devices, and describe their observed landing screens. This process creates a verified and grounded deeplink catalog that pairs each working deeplink with a description of its landing screen. Using this catalog, we introduce GUI-Hopper, a improves task success in commercial applications on real devices, further demonstrating the benefits of hybrid interaction.
Read the full abstract ▾
All authors Yuchen Sun, Chenglin Cai, Gongjie Zhang, Tianyu Xia, Quyu Kong, Panrong Tong, Zhengwen Zeng, Long Chen, Steven Hoi, Chongyang Zhang, Yue Wang
Artificial Intelligence · Cross-listed from physics.soc-ph
Warned alike, AI agents avoid the less-crowded road while people take it
Takahiro Ezaki, Naoto Imura and Katsuhiro Nishinari
AI
agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocated. We tested this feedback in a two-road congestion game. Adding one sentence warning that others might follow a routing tip made populations of 50 GPT
agents crowd one road while avoiding the nearly empty alternative. Average travel time rose from 64 to 95 min, although any crowded-road
agent could have saved 69 min by switching alone. The warning discouraged the very move it predicted. The pattern persisted for 100 rounds. Two other model families shifted the same way without locking onto one road. Twelve all-human groups (240 participants) stayed near balance under numerical reports or the tip and warning. In 24 mixed groups with a further 240 participants, imbalance grew with the share of
agents in the registered analysis, while people increasingly took the road the
agents avoided. Collective costs stayed below the allagent reference, but with 15
agents and 5 humans,
agent seats averaged 80 min, compared with 44 min for human seats. Shared forecasts can thus sustain collective inefficiency among similar
agents. A better group average can also hide an unequal burden. Evaluations of AI
agents that share resources should test populations, treat messages as interventions and report who bears the costs.
Read the full abstract ▾
Artificial Intelligence
EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting
Seunghan Lee, Sangjun Han, Jun Seo et al. (+9 more)
Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has properties that such corpora rarely contain: Short histories, frequent zeros, censoring by stock-outs, and exogenous events that the series does not record. To this end, we propose EXAONE Demand, built on 1) a demand-specific corpus and 2) a demand-aware adapter. For the corpus, we assemble 11.3M series and 48.4B observations from 73 sources, and a synthetic generator supplies the behaviour that open demand data under-represents. For the adapter, we attach low-rank branches to a frozen general-domain backbone, one for each of the four demand classes (smooth, intermittent, erratic, and lumpy), and a router that reads eight scale-free statistics of the input series decides how much each branch contributes. We build EXAONE Demand in two versions, one trained on real-world and synthetic demand together and one trained on the synthetic corpus alone. On 22 held-out
datasets, both versions outperform 36 TSFMs, and real-world demand adds a gain over synthetic data alone.
Read the full abstract ▾
All authors Seunghan Lee, Sangjun Han, Jun Seo, Junhyeok Kang, Jaehoon Lee, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Soonyoung Lee, Wonbin Ahn
Artificial Intelligence
TISD: On-Policy Self-Distillation with Trajectory Intervention
Taeckyung Lee, Rinat Amankos, Jeonghye Kim et al. (+3 more)
On-policy self-
distillation (OPSD) provides dense teacher targets, but evaluates them only along student-sampled rollouts. When the privileged teacher favors an alternative action at a visited prefix, OPSD can provide a target for the branch decision but cannot supervise the successor contexts induced by that action unless the student samples it. This creates a training-time data-collection bottleneck and suggests a different role for teacher-student disagreement: proposing a trajectory branch rather than identifying a sufficient local repair. Our diagnostic framework using controlled
token interventions reveals that a teacher-preferred
token at peak disagreement can improve student continuation success, while its local corrective value is limited. Motivated by this finding, we introduce a simple branch-regenerate-distill
algorithm, Trajectory-Intervention Self-
Distillation (TISD). TISD forces a teacher-selected branch action, returns suffix generation to the student, and distills the full trajectory under the privileged-context-conditioned teacher. Across the coding models, TISD improves average Avg@4 over SDPO by 1.2 percentage points. Across the science domains, it improves average Avg@128 by 0.8 points under an equal-step budget and by 0.3 points under an equal-time budget. These results support teacher-guided branching as a way to expose useful successor contexts for self-
distillation.
Read the full abstract ▾
All authors Taeckyung Lee, Rinat Amankos, Jeonghye Kim, Hyungjun Yoon, Woogyeol Jin, Sung-Ju Lee
Artificial Intelligence · Cross-listed from cs.CL
Haixu Ma, Saad Lahrichi, Weiwei Li et al. (+11 more)
Black-box On-Policy
Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not
token probabilities.
Adversarial distillation offers one route: it learns a discriminator over
prompt-matched teacher and student responses and uses its score as the policy reward. However, sampling discriminator negatives from the latest student at each step couples the learned reward to a negative distribution that changes after every policy update. We address this moving-target problem with persistent-negative
adversarial distillation, a live-pool method that replaces a fraction of each discriminator batch with historical,
prompt-matched teacher–student comparisons. Under matched discriminator compute, historical comparisons train the discriminator, while GRPO remains on-policy with fresh student responses. Our analysis identifies the Bayes-optimal reward as a teacher-to-negative log-density ratio and, under explicit assumptions, shows how persistent negatives anchor the discriminator and reduce reward-estimation MSE relative to fresh-negative training. Across two student families, three judges, and four judged-chat
benchmarks, persistent-negative
adversarial distillation consistently improves performance over current methods at matched discriminator compute. It also yields smoother fresh-policy discriminator trajectories, with fewer below-chance dips. These findings identify the discriminator's negative distribution as an important design axis in black-box on-policy
distillation.
Read the full abstract ▾
All authors Haixu Ma, Saad Lahrichi, Weiwei Li, Kevin Han, Weiqiang Wu, Peggy Yang, Dongzhuo Li, Ruiyi Li, Serena Li, Gedi Zhou, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Lizhu Zhang
Artificial Intelligence · Cross-listed from cs.SE
Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development
Viktor Kjellberg, Srijita Basu, Simin Sun et al. (+2 more)
The emergence of AI
agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating development tasks with increasing autonomy. This transition is particularly significant for embedded software organizations, where strict requirements for quality, traceability, verification, and long-term maintainability often apply. This paper presents a case study of a large embedded systems company and its transition toward becoming an AI-first organization. Through a mixed method, we analyzed data collected from a semi-structured workshop with 40 participants, including scrum masters, architects, management, and product owners. The findings show that the participants expect agentic AI to affect team structure, required competencies, organizational strategies, and developers' roles within the organization. Based on these findings, the paper discusses implications for
federated AI team formation, human-in-the-loop practices in such an organization, and the sustainable adoption of AI
agents in embedded software engineering. We also present a concrete roadmap for the organization towards becoming an AI-first organization.
Read the full abstract ▾
All authors Viktor Kjellberg, Srijita Basu, Simin Sun, Farnaz Fotrousi, Miroslaw Staron
Artificial Intelligence
SkillEvoReg: Regularizing Agent Skill Evolution Against Overfitting
Guanyu Nie, Fangzhou Zhu, Shixiong Kai et al. (+3 more)
Language-model
agents increasingly improve by converting execution experience into reusable external skills. Yet repeated skill updates form a learning process of their own: locally useful edits can accumulate into redundant or task-specific instructions, while new updates can disrupt behavior that previously worked. We study this problem as skill-
evolution overfitting and introduce SkillEvoReg, a general regularization framework for skill
evolution inspired by anti-overfitting techniques in neural-network training. SkillEvoReg combines training-time skill dropout, which perturbs update generation, and complexity-aware local regularization, which controls unnecessary structural growth, with causal counterexample validation (CCV), which provides targeted behavioral validation of candidate-specific regressions. We instantiate the framework across heterogeneous skill-
evolution systems while retaining each system's native skill evolver and task evaluator. Across SkillOpt, SkillEvolBench, and ContinualSkillBench, SkillEvoReg consistently controls skill-state growth while preserving competitive downstream capability, improves several transfer and later-stage
evolution outcomes, and identifies update-level regressions that structural metrics alone cannot reveal. These results suggest that explicit regularization is a useful complement to increasingly capable skill updaters.
Read the full abstract ▾
All authors Guanyu Nie, Fangzhou Zhu, Shixiong Kai, Xiongwei Han, Tao Zhong, Mingxuan Yuan
Artificial Intelligence
Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis
Thong Bach, Dung Nguyen, Thao Minh Le et al. (+1 more)
Existing attacks and defenses for
diffusion-based large
language models (dLLMs) target specific vulnerabilities but lack a shared framework explaining why attacks succeed. We propose one by interpreting safety
alignment as shaping the denoising energy landscape: a well-aligned model routes harmful queries toward safe outputs through an energy barrier that separates the two regions. Current jailbreak attacks reduce to two strategies for circumventing this barrier: obscuring the query's safety disposition at initialisation, or intervening mid-trajectory to force the denoising path across the energy barrier. From this perspective and the result that masked
diffusion models minimise kinetic energy during denoising, we derive three complementary, training-free detection signals: a step-0 ratio that reads the initial safety disposition from the logit distribution before generation begins, and two trajectory-velocity signals that track kinetic energy in complementary subspaces of the logit space. An attack must either reveal its intent at initialisation or expend kinetic energy to cross the barrier in at least one monitored subspace, so the three signals cover each other's blind spots in the energy budget by construction. Evaluation across three dense dLLMs (LLaDA-8B, LLaDA-1.5, Dream-7B) and a sparse mixture-of-experts dLLM (LLaDA-MoE-7B) confirms this complementarity. In stress tests of known attacks, every configuration that evades detection also fails to produce harmful content, suggesting that the detection and barrier-crossing thresholds are hard to separate.
Read the full abstract ▾
All authors Thong Bach, Dung Nguyen, Thao Minh Le, Truyen Tran
Artificial Intelligence · Cross-listed from cs.LG
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Tianze Xu, Yanzhao Zheng, Zhentao Zhang et al. (+10 more)
Multi-teacher on-policy
distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes each
prompt to a domain-matched teacher for the entire rollout. This dependence on
prompt-level domain labels restricts using unlabeled training mixtures and leaves complementary signals from other teachers unused. We introduce MOPD-Router, a framework that routes supervision over the full teacher pool at each
token, without domain labels or training a separate routing model. Its plug-in interface supports different metrics for selecting and weighting teacher-specific OPD signals. Within this interface, we propose ExpertAlign, which scores each teacher by whether its correction to the student at the current
token expresses the specialization that teacher acquired during post-training, and compare it against two reference metrics built on teacher confidence (
Entropy) and teacher-student discrepancy (Novelty). Experiments on unlabeled and domain-labeled training mixtures under strong-to-weak and same-size
distillation scenarios show that ExpertAlign achieves the strongest overall performance in all four settings. On unlabeled data, it improves the overall score by 5.88 (+12.3%) points over Mean aggregation; on domain-labeled data, it outperforms standard MOPD by 3.95 (+7.8%) points without using available domain labels. These results demonstrate
token-level routing can exploit cross-domain complementary supervision, and reduce exclusive reliance on
prompt-level domain assignment. Code is available at: https://github.com/TURLEing/MOPD-Router.
Read the full abstract ▾
All authors Tianze Xu, Yanzhao Zheng, Zhentao Zhang, Yuanqiang Yu, Chao Ma, Jihuai Zhu, Lelun Wu, Lyumanshan Ye, Pengfei Liu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu
Artificial Intelligence
PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices
Minghui Yu, Ke Mu and Gang Wu
Deploying small
language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge: their limited
reasoning capacity hinders reliable execution of multi-step
agent tasks requiring complex tool orchestration. Existing plan-solve paradigms rely on
prompt-based enforcement, which our experiments show SLMs almost entirely disregard: weak models fail to invoke the plan. We propose PTC-Decoder (Plan-Tool Constrained Decoder), a training-free, plug-and-play decoder framework that combines (1) a Plan-to-Act paradigm, which elevates planning to an atomic tool and forces its invocation at the first inference step, and (2) TC-Decoder, a deterministic finite automaton that imposes
token-level hard constraints on tool names while preserving freedom over parameter generation, thereby retaining SLM
reasoning capability. Evaluated on 200 real remote-sensing satellite tasks across 7 SLMs, PTC-Decoder yields a statistically significant mean overall score gain of +1.21 (p<0.01), 95% CI [+1.13, +1.29]), with consistent improvements across models and other
datasets. An ablation study that removes TC-Decoder causes substantial performance degradation across all quality metrics without reducing computational cost, confirming TC-Decoder as the primary driver. PTC-Decoder thus offers a lightweight yet effective solution for improving step-level reliability, with final-answer accuracy remaining an open challenge. In essence, we enforce plan adherence by constraining the permissible output vocabulary during inference, without requiring retraining.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Subject-Invariant Cross-Modal Decoding of Perceived Speech from Brain Recordings
Aoke Zhang and Jing Chen
Perceived
speech decoding based on non-invasive
brain-computer interface (BCI) signals has been extensively studied in recent years. Research in this field primarily faces two challenges: extracting neural representations with rich spatiotemporal information and achieving cross-subject generalization. Although separate studies have proposed methods to cope with these issues, a unified approach that simultaneously tackles both challenges remains lacking. To fill this gap, we propose the Subject-Invariant Cross-Modal Perceived
Speech Decoding (SICMD) method, which integrates functional
magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). We conduct comprehensive analyses of the fusion method, fusion position, encoder architecture, and model inputs. Our results demonstrate that the proposed method improves Top-1, Top-10, and Rankacc by more than 10.6%, 10.1%, and 1.7%, respectively, compared to baseline methods in cross-subject perceived
speech decoding tasks, while reducing training costs by 88.8% and 60.5% compared to multi-subject and intra-subject decoding settings. Further visualization experiments also confirm the effectiveness of our approach.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Evaluation Is All You Need for Multi-Modal Autonomous Driving
Zeyu He, Shiqi Liu, Ke Chen et al. (+14 more)
Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing methods mainly focus on improving trajectory multi-modality, enhancing trajectory representations, or reshaping the candidate distribution. Nevertheless, we identify a pronounced generation-evaluation asymmetry in multi-modal planning: despite strong oracle performance, existing planners often fail to reliably select the best available candidate, leaving substantial planning potential unrealized. To address this challenge, we propose iDriveVLA, a multi-modal planning framework that improves the candidate trajectory space while enabling more reliable and context-aware trajectory evaluation. Specifically, iDriveVLA introduces a unified trajectory evaluator comprising a Safety-aware Scorer for quality and risk estimation, together with a VLM-guided Modulator for scene-adaptive criterion weighting. We further develop an oracle-aligned progressive training strategy consisting of candidate imitation pretraining, candidate space refinement, and semantic ranking
alignment. On the public NAVSIM v1 leaderboard, iDriveVLA achieves a new state-of-the-art performance of 94.95 PDMS, surpassing the human-expert reference.
Read the full abstract ▾
All authors Zeyu He, Shiqi Liu, Ke Chen, Yun Yan, Jinzi Wu, Dianqiao Lei, Sirui Wang, ShuRui Peng, Tao Chen, Zhuo Huang, Yu Wu, Yadong Shao, Zhichao Li, Ke Sun, Yang Guan, Keqiang Li, Shengbo Eben Li
Artificial Intelligence
A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory
Xiaoyang Li, Yiqi Wang, Chencheng Zhu et al. (+6 more)
Evaluating claim admission in shared
agent memory is challenging because repeated claims may be mistaken for independent evidence. An
agent may copy or paraphrase a retrieved belief, while admitting a false claim exposes subsequent
agents to it. To study this problem, we introduce the Correlated Promotion
Benchmark (CPB), which evaluates whether candidate claims should be admitted to shared
memory.CPB-Static constructs a frozen test split from publicly annotated sources with fixed gold actions. CPB-Live runs multi-
agent teams over a shared store, records all writes and
retrievals, and tracks source lineage defined by each scenario. A separate consumer answers from the store alone. We evaluate eight admission policies across four
agent families. Our results show that policies which deduplicate sources reject many true claims alongside false ones, whereas policies preserving answer coverage admit nearly as many false claims as unrestricted sharing. Gating on declared source type reduces false adoption to 0.06–0.09, compared with 0.22–0.47 for other answering policies. Once an uncontested false belief enters
memory, the consumer asserts it in 0.97–0.99 of probes across all families. No non-oracle policy consistently rejects false claims across verbatim copies, paraphrases, and paraphrases declared authoritative. These findings reveal the limitations of admission policies without access to source lineage.
Read the full abstract ▾
All authors Xiaoyang Li, Yiqi Wang, Chencheng Zhu, KE XU, Wencheng Yang, Zequn Sun, Pingan Song, Yiqun Duan, Taotao Cai
Artificial Intelligence · Cross-listed from cs.CR
XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security
Sangshin Park, Jainta Paul, Lawrence Ponce et al. (+3 more)
Industrial control system attacks are usually documented in terms of the plant where they occurred: its sensors, actuators, process stages, and control logic. Yet many attacks express a more general physical pattern–such as suppressing flow, corrupting chemical dosing, or driving a vessel toward overflow–that may also matter in a different plant. The challenge is deciding when such a threat remains meaningful on a new system rather than relying on similar component names or broad semantic labels. We present XPhysICS, a methodology for grounding documented cyber-physical threats onto a specific target system. XPhysICS converts source evidence into a provenance-linked description of what is manipulated, what physical consequence is expected, and what observations the evidence calls for. Once this analyst-guided abstraction, its vocabulary and schema version, and a target contract are fixed, XPhysICS applies deterministic grounding checks. An accepted result can be represented as a validation slice that records the mapped roles, signals, dependencies, and context intended to support later evaluation. We study 83 threat abstractions across continuous-process and manufacturing sources using separate evaluation denominators. The continuous-process study evaluates 78 abstractions against target contracts spanning water treatment, water distribution, hydropower, and chemical processes. Selected cases are exercised through controlled perturbations of simulator-role signals. We also test compatibility with several analysis styles, including the released upstream GeCo implementation, and conduct a three-objective, one-target realizability study using a paper-derived search reproduction. Across these evaluated settings, the results support treating explicit target checks and traceable evidence as separate from semantic similarity alone.
Read the full abstract ▾
All authors Sangshin Park, Jainta Paul, Lawrence Ponce, Md Raihan Ahmed, Mu Zhang, Luis Garcia
Artificial Intelligence
Evaluating Real-Time Voice Agents: From Component Quality to Grounded Outcomes
Shivam Negi, Arpit Rawat and Rashi Jain
Real-time voice
agents have moved from research prototypes to production deployments, yet the literature describing them is fragmented across three communities that rarely cite one another:
speech foundation modelling, turn-taking psycholinguistics, and agentic evaluation. Architecture papers report latency, turn-taking papers report prediction accuracy, and agentic
benchmarks report task success, so no single number describes whether a deployed
agent is actually good. We address that gap with three evidence-based claims, each traceable to a corpus of 38 primary sources organised into an application-centric taxonomy of six categories. First, architecture choice is a deployment constraint rather than a settled verdict: a 2026 enterprise tutorial reports that no fully self-hostable end-to-end system yet meets production constraints, while a chunked cascade independently reaches state-of-the-art duplex behaviour, showing duplex behaviour is separable from duplex architecture. Second, evaluation has shifted decisively from component quality toward grounded outcomes, with recent
benchmarks verifying backend state rather than trusting what the
agent claims to have done. Third, the dyadic assumption in most models and
benchmarks is breaking down: multiparty turn-taking and multi-speaker
reasoning benchmarks show that deciding when not to speak, and
reasoning about who may be told what, are first-class capabilities two-participant framings cannot measure. For each source we state the problem it targets, its mechanism, and its reported evidence, alongside the search strategy, inclusion criteria, and a verification step that caught a misattributed arXiv identifier in circulation. We propose TRG (Timing-Recovery-Grounded), a reporting standard characterising an
agent by timing, post-disruption recovery, and state-verified outcome together, with a conditional fourth axis for multiparty deployments.
Read the full abstract ▾
Artificial Intelligence
HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents
Zihong He, Junxiao Shen, Chen Liang et al. (+1 more)
Text-based
memory and context compression support reuse of past interactions. Resizing continuous
memory changes the input to a frozen LLM, coupling capacity allocation with readout. We propose Hard-Origin Adaptively Softened
Memory (HasMem). Frozen hard-
prompt embeddings provide a verifiable initial state. A controller adjusts
memory widths, a Writer re-encodes resized entries, and Reader and Global provide readout adaptation and cross-turn state. On all $535$ questions in a reconstruction probe derived from the Multi-Session Chat (MSC) development split, the main configuration achieves lexical F1 of $95.3$ ($+4.4$ percentage points) at $93.6\%$ of the hard reference's framed
memory positions. With approximately matched per-question target body budgets, six configurations at mean per-entry retention around $0.83$–$0.91$ exceed rule-based re-encoding by $8.0$–$23.6$ exact-match (EM) percentage points. With fixed model parameters and rule target width ratio $0.75$, Global's EM gain passes a user-level exact paired test with Bonferroni correction over eight comparisons. On all $500$ LongMemEval-S questions, local lexical F1 rises from the hard reference's $3.4$ to $8.9$, and answer negative log-likelihood (NLL) falls from $12.257$ to $5.274$. F1 gains accompany lower EM on both evaluations.
Read the full abstract ▾
All authors Zihong He, Junxiao Shen, Chen Liang, Hai-Ning Liang
Artificial Intelligence
ConsultMind:Towards Automated Diagnostic Consultation via Uncertainty-Aware Reasoning
Xiao Sun, Yuming Yang, Yun Chen et al. (+9 more)
Diagnostic consultation is an online sequential decision-making process in which clinicians gather evidence through patient interaction until a diagnosis is sufficiently supported. Automating this process requires adaptive inquiry and interpretable decisions.
Bayesian networks offer a natural foundation by updating diagnostic posteriors as evidence accumulates, but their use in open-ended consultation raises two challenges: linking diagnostic hypotheses to potential inquiries and translating evolving posteriors into consultation decisions. We introduce AutoDisym, an automated pipeline that integrates diagnostic knowledge with heterogeneous diagnosis-labeled clinical narratives to construct a Disorder–Symptom
Bayesian Network (DSBN). Building on the DSBN, we propose ConsultMind, an uncertainty-aware framework that updates disorder posteriors after each response and uses posterior uncertainty to guide inquiry and diagnosis. We evaluate both methods across psychiatry, respiratory medicine, fever clinics, and three public
datasets. The results show that AutoDisym can automatically construct high-quality DSBNs and that ConsultMind consistently improves diagnostic performance and explanation soundness. For example, AutoDisym achieves macro-averaged F1 scores of 81.37 for canonical symptoms and 72.19 for manifestations using GPT-5.6-Sol. ConsultMind improves Top-1 and Top-3 diagnostic accuracy by up to 22.15 and 37.89 percentage points, respectively. Physician evaluation further shows that ConsultMind improves the quality of ranking explanations, differential diagnoses, and diagnosis rationales across LLMs of different scales. This work offers a promising approach to automatic diagnostic consultation.
Read the full abstract ▾
All authors Xiao Sun, Yuming Yang, Yun Chen, Jiang Zhong, Junnan Zhu, Xinyi Jiang, Haoyang Zeng, Ruirui Chen, Yining Wang, Xinyu Zhou, Rong Tang, Kaiwen Wei
Artificial Intelligence · Cross-listed from cs.CV
Tianhang Guo, Yulin He, Wei Chen et al. (+3 more)
Reasoning segmentation aims to interpret implicit textual queries and enable fine-grained visual perception, which is critical for applications such as human-computer interaction and
embodied agents. Existing methods typically generate explicit Chain-of-Thought (CoT) by
multimodal large
language models (MLLMs) before localizing the target. Although intuitive, such explicit verbal
reasoning introduces substantial
attention interference: redundant textual
tokens disrupt
attention during perception-
token generation and also increase the effective distance between visual
tokens. To address this issue, we propose LIRSeg, which fully replaces explicit CoT with a compact set of learnable latent
tokens for
reasoning segmentation. LIRSeg is trained in two stages: spatial
alignment grounds the latent
tokens in object-relevant visual evidence, and GRPO further optimizes them with
segmentation rewards. To make these compact latent
tokens more informative, we introduce three complementary mechanisms from an information perspective: extreme-advantage sampling for selecting informative training signals, decoupled exploration-stability updates for learning complementary representations, and latent diversity amplification for preventing representational collapse. Extensive experiments on
benchmarks demonstrate that LIRSeg consistently improves both
segmentation accuracy and
reasoning efficiency. Compared with the VisionReasoner baseline, LIRSeg achieves absolute gIoU improvements of 4.9% on ReasonSeg, 7.1% on MUSE, and 4.7% on MMR, while achieving a approximately 16x reduction in
reasoning tokens. Code is available in supplementary materials.
Read the full abstract ▾
All authors Tianhang Guo, Yulin He, Wei Chen, Wenjuan Zhou, Yuhang Li, Xinbiao Gan