Artificial Intelligence · Cross-listed from cs.LG
CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning
Naimur Rahman Chowdhury, Shatabdi Sen Prapti, Md. Salehin Seyam et al. (+1 more)
Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs operate in a decentralized network of local centers that face uncertain local demand and supply dynamics, resulting in inconsistent avail- ability of local services. Redistribution of supplies among these local centers reduces these imbalances, but the centers often make decisions independently, with limited information and disrupted transportation. This study develops CoRe-MARL, a cooperative multi-
agent reinforcement learning (MARL) framework, by formulating a decentralized partially observable Markov decision process (Dec-POMDP). We treat each center as an
agent that learns a redistribution policy to improve the service in the worst-case region and reduce the service gap across regions while protecting network-wide service. We incorporate a recurrent network that captures evolving supply and demand dynamics without direct observation, while multi-
agent proximal policy optimization (MAPPO) enables centralized training and decentralized execution (CTDE). We evaluate the framework in a simulated environment with diverse trajectories, where exact dynamics are not observed by actors and the MAPPO critic. We compare the recurrent MAPPO with the recurrent independent PPO (IPPO) and a local only heuristic, and find that MAPPO reduces the service gap across local centers and enhances service for the worst-served center while maintaining competitive network-wide service. The recurrent MAPPO also shows consistent performance across diverse trajectory patterns, demonstrating its ability to adapt to evolving dynamics. The findings demonstrate the capability of cooperative learning for decentralized redistribution and improving equitable service under uncertain and evolving dynamics.
Read the full abstract ▾
All authors Naimur Rahman Chowdhury, Shatabdi Sen Prapti, Md. Salehin Seyam, Limon Bin Hossain
Artificial Intelligence · Cross-listed from cs.CV
GenStream: Semantic Streaming Framework for Generative Reconstruction of Human-centric Media
Emanuele Artioli, Daniele Lorenzi, Shivi Vats et al. (+2 more)
Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or interactive media. Standard codecs re-encode entire frames, foreground and background alike, treating all pixels uniformly and ignoring the semantic structure of the scene. This leads to significant bandwidth waste, particularly in scenarios where backgrounds are static and motion is constrained to a few salient actors. We introduce GenStream, a semantic streaming framework that replaces dense
video frames with compact, structured metadata. Instead of transmitting pixels, GenStream encodes each scene as a combination of skeletal keypoints, camera viewpoint parameters, and a static 3D background model. These elements are transmitted to the client, where a generative model reconstructs photorealistic human figures and composites them into the 3D scene from the original viewpoint. This paradigm enables extreme compression, achieving over 99.9% bandwidth reduction compared to HEVC for the continuous data stream. We partially validate GenStream on Olympic figure skating footage and demonstrate potential for high perceptual fidelity under minimal data. While acknowledging the significant computational costs shifted to the client and challenges in generalization, GenStream opens new directions in volumetric avatar synthesis, canonical 3D actor fusion across views, and personalized viewing experiences, laying the groundwork for scalable, intelligent streaming in the post-codec era.
Read the full abstract ▾
All authors Emanuele Artioli, Daniele Lorenzi, Shivi Vats, Farzad Tashtarian, Christian Timmerer
Artificial Intelligence · Cross-listed from cs.CL
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
Mika Okamoto and Ansel Kaplan Erol
As corporate AI adoption continues to grow, enterprise-grade LLM
agents are being deployed into sensitive contexts such as hiring, healthcare, and finance. In these contexts, compliance with rules specified in an
agent's system context is a first-order legal concern. Currently, no evaluation framework systematically measures which LLM models tend to violate compliance rules, especially under pressure from a persistent user, a hurried manager, or circumstances where violation is convenient or attractive. We introduce PACT (Pressure-Applied Compliance Testing), a
benchmark for rule-following under pressure in AI
agents assisting employees in daily tasks across twelve regulated enterprise domains and forty-eight scenarios, each set in a realistic multi-turn conversation. Each
benchmark item pairs a standing rule against a rule-violating shortcut, and applies a battery of pressures across different wordings and system-
prompt modes. We construct PACT component by component under strict LLM-as-judge
auditing to ensure samples are unambiguous, ungameable, and realistic enough to avoid eliciting evaluation-aware behavior. We use PACT to profile LLM compliance across six complementary metrics that create a holistic picture of an AI assistant's robustness under pressure and throughout multi-turn conversations, its transparency, and ability to correctly discern where a rule applies. We aggregate this profile into PACTScore, a reliability-weighted compliance rate over all items and modes. Our results across 22 common LLM models spanning multiple providers and sizes show substantial variability in compliance across models and metric dimensions. Even the strongest assistants mis-apply a rule on 6 to 10% of items, and ordinary user pressure raises the violation rate by 65% on average. PACT highlights compliance risks in LLM assistants, motivating guardrails and careful model selection.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Online Robust Reinforcement Learning Through Monte-Carlo Planning
Tuan Dam, Kishan Panaganti, Brahim Driss et al. (+1 more)
Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real-world dynamics are identical. Although this assumption helps achieve the success of MCTS in games like Chess, Go, and Shogi, the real-world scenarios incur ambiguity due to their modeling mismatches in low-fidelity simulators. In this work, we present a new robust variant of MCTS that mitigates dynamical model ambiguities. Our
algorithm addresses transition dynamics and reward distribution ambiguities to bridge the gap between simulation-based planning and real-world deployment. We incorporate a robust power mean backup operator and carefully designed exploration bonuses to ensure finite-sample convergence at every node in the search tree. We show that our
algorithm achieves a convergence rate of $\mathcal{O}(n^{-1/2})$ for the value estimation at the root node, comparable to that of standard MCTS. Finally, we provide empirical evidence that our method achieves robust performance in planning problems even under significant ambiguity in the underlying reward distribution and transition dynamics.
Read the full abstract ▾
All authors Tuan Dam, Kishan Panaganti, Brahim Driss, Adam Wierman
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
Izumi Takahara, Kazunori Nishio, Akira Aiba et al. (+4 more)
Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the output is a set of optimized samples, with the measurements reduced to predefined scalar objectives and the reasons behind success left unarticulated. Here we present SynAgent, a framework in which large
language model
agents operate an automated experimental system and maintain an explicit, revisable understanding of the synthesis process as the campaign's primary output. Starting with no predefined analysis pipeline, SynAgent adaptively generates analysis skills for newly acquired data and evolves this understanding through
multimodal reasoning over experimental data such as X-ray diffraction patterns and electron micrographs. The
evolution is guided by a verify-falsify scheme, in which the
agent deliberately challenges its own hypotheses by testing conditions predicted to fail as well as those predicted to succeed. In a single campaign of 18 autonomous experiments using LiCoO2 (001) thin-film deposition as a testbed, SynAgent synthesized highly crystalline films and evolved an understanding of how the substrate temperature governs crystallization, discovering an abrupt threshold and a narrow optimal growth window at 650-690 {\deg}C. These results extend autonomous experimentation beyond optimized samples to testable, human-readable understanding.
Read the full abstract ▾
All authors Izumi Takahara, Kazunori Nishio, Akira Aiba, Shigeru Kobayashi, Takao Nakajima, Taro Hitosugi, Teruyasu Mizoguchi
Artificial Intelligence
Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection
Ziyi Zhou, Xiaoming Zhang, Hui Pang et al. (+5 more)
Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily rely on supervised GNN-based models, which require substantial labeled data and exhibit limited generalization. Although large
language models (LLMs) exhibit strong
reasoning capabilities, directly feeding them raw propagation graphs creates a significant modality mismatch and severe information overload, making structure-aware
reasoning unreliable in zero-shot and few-shot settings. To bridge this gap, we propose MAGER, a multi-
agent genetic
evolution framework that automatically discovers meta-paths optimized for LLM
reasoning. By compressing complex propagation graphs into informative subgraphs, the evolved meta-paths alleviate both information overload and modality mismatch, enabling frozen LLMs to perform structure-aware veracity
reasoning. We further introduce a graph in-context learning strategy that retrieves semantically and structurally similar demonstrations to strengthen classification and
reasoning. Extensive experiments show that MAGER substantially improves frozen LLMs as standalone fake news detectors in data-efficient settings. Our code is available at https://github.com/SenticNet/MAGER.
Read the full abstract ▾
All authors Ziyi Zhou, Xiaoming Zhang, Hui Pang, Yuting Zhang, Tiesunlong Shen, Bingyu Yan, Erik Cambria, Litian Zhang
Artificial Intelligence
Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making
Yu Liu, Wenwen Li, Yifan Dou et al. (+1 more)
In-context learning (ICL) enables large
language model (LLM)
agents to improve decisions using interaction history, yet it remains unclear whether such improvement reflects refined internal
reasoning or mere extrapolation of statistical patterns. To disentangle these mechanisms, we study LLM
agents in multi-
agent incomplete-information games that require recursive belief
reasoning. By constructing a public goods game and manipulating the statistical structure of historical feedback, we evaluate decision quality against a history-independent rational expectations
equilibrium (REE)
benchmark. Our experiments reveal that when historical statistical patterns are disrupted, the benefits of longer context largely vanish, degrading decision quality to the no-context baseline in a way sharply amplified by stronger strategic interdependence. These results suggest that, in such strategic environments, ICL behavior is more consistent with statistical extrapolation than with strategic
reasoning. Our work extends the mechanistic study of ICL to strategic multi-
agent settings, introduces REE as a diagnostic tool for distinguishing
reasoning from extrapolation, and provides a reusable framework for probing the boundaries of LLM
reasoning in recursive belief tasks.
Read the full abstract ▾
All authors Yu Liu, Wenwen Li, Yifan Dou, Guangnan Ye
Artificial Intelligence · Cross-listed from cs.LG
Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
Naveen Vakada, Mingyuan Li and Shaoxiong Ji
Test-time reinforcement learning (TTRL) enables models to improve their
reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises a natural question: can effective test-time adaptation emerge when both the reward signal and the optimization space are severely restricted? We answer this question with label-free bias-only TTRL, which uses majority-vote pseudolabels as rewards and optimizes only ~100K bias parameters while keeping the pretrained backbone frozen. On MATH-500, our approach reaches 76.67% accuracy with Qwen2.5-7B, slightly exceeding our own labeled bias-steering reproduction while optimizing 76,000x fewer parameters than full-parameter TTRL. The same training procedure improves performance across
vision-
language and audio
reasoning tasks, including MathVista, AI2D, LogicVista, and MMAU. We further show that the learned steering vectors transfer to 4,500 held-out MATH problems, indicating that the adaptation is not limited to the problems used during test-time optimization. Finally, we analyze why this highly restricted adaptation can work, showing that majority-vote reliability improves with rollout consensus and that bias subspaces with greater accessible gradient energy exhibit stronger downstream trainability. These results demonstrate that substantial test-time adaptation can emerge from optimizing a tiny bias-only subspace using entirely label-free rewards.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
On-the-Fly Homographies Calibration for Multi-Camera Tracking
David Voihanski, Mor Sinai and Ben Zion Bobrovsky
Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments.
Privacy regulations frequently prohibit recording
video for offline calibration; limited bandwidth precludes synchronizing high-resolution streams from hundreds of cameras; and covering immense physical sites with calibration targets is logistically infeasible. We present a multi-camera homography calibration system designed to overcome these barriers through "on-the-fly"
geometric refinement. Starting from coarse manual homographies, we introduce a centroid-based projection optimization (PO) that continuously aligns the ground-plane geometry using live detection streams. Because PO operates asynchronously on already-transmitted, lightweight metadata, it adds zero computational latency to the real-time tracker. This allows the system to adapt automatically to camera movements or environmental changes without human intervention. This optimized geometry feeds a multi-camera bird's-eye-view (BEV) tracker that fuses detections and unifies trajectories across zones. Crucially, by operating strictly on live anonymous metadata, our solution ensures a
privacy-safe, zero-overhead, and resilient tracking pipeline that maintains global consistency in dynamic environments where static, recorded-
video calibration is impossible.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations
Marcin Lawenda, Aleksandra Krasicka, David Caballero et al. (+2 more)
Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble member. We ask how well deep learning surrogates can reproduce these simulations at a fraction of this cost, training them on 10,584 fire spread simulations at 2m resolution for the Rectoret region in Catalonia, Spain. Four architectures are compared: a patch-based U-Net, a transfer-learned ResNet-50, a physics-informed network constrained by the wind-driven advection equation and a Swin-Unet
transformer. Among the terrain and vegetation variables, only surface fuel load predicts burn probability with any strength (r = 0.27) and including it lowers prediction error by 21%. The remaining variables correlate weakly and are highly duplicative. Next, an experiment with saliency, occlusion and rotation demonstrates the models' learning. Convolutional models rely primarily on distance from the current fire front, while Swin-Unet assigns more weight to fuel and terrain, a finding also noted in an unrelated wildfire
dataset. When applied without retraining to the second region, Pedriza, all three convolutional models still predict fire spread, losing accuracy by a small but systematic margin.
Read the full abstract ▾
All authors Marcin Lawenda, Aleksandra Krasicka, David Caballero, Luis Torres, Łukasz Szustak
Artificial Intelligence
TRIPROBE: Probing Task Separability Beyond Classification for XAI
Amirhossein Sadough, Freek Hens, Aleksa Bokšan et al. (+2 more)
Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG
benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.
Read the full abstract ▾
All authors Amirhossein Sadough, Freek Hens, Aleksa Bokšan, Mohammad Mahdi Dehshibi, Mahyar Shahsavari
Artificial Intelligence · Cross-listed from cs.SD
Aaron Yee, Fengjie Lu, Jiarui Hai et al. (+5 more)
Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and
videos. Existing
benchmarks and models have advanced semantic search over spoken content, but largely focus on what is said while overlooking who says it. In many real-world scenarios, however, users need to retrieve
speech based jointly on semantic content and a target speaker, where the speaker may be specified naturally through a reference
speech utterance rather than a predefined identity. To address this gap, we introduce VoiceTrace-Bench, a
benchmark for hybrid
speech retrieval in which each query combines text specifying what to retrieve with reference
speech specifying who to retrieve. This setting requires models to integrate complementary semantic and speaker information directly from heterogeneous query inputs. Motivated by the joint audio-text modeling capabilities of audio-
language models (ALMs), we develop VoiceTrace, a two-stage
retrieval framework consisting of VoiceTrace-Emb, an
embedding model that learns unified representations for efficient large-scale
retrieval, and VoiceTrace-Reranker, a reranking model that jointly examines each query–candidate pair for fine-grained relevance estimation. Experiments show that VoiceTrace achieves state-of-the-art performance on established semantic
speech retrieval benchmarks, while substantially outperforming cascade-based approaches on VoiceTrace-Bench, demonstrating its effectiveness for both conventional semantic
retrieval and the new hybrid
retrieval setting.
Read the full abstract ▾
All authors Aaron Yee, Fengjie Lu, Jiarui Hai, Chenang Jiang, Helin Wang, Siwei Tu, Weitao You, Lingyun Sun
Artificial Intelligence
AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution
Jiabin Lou, Yirong Yang, Haopeng Wang et al. (+6 more)
Collective intelligence is a collaborative autonomy paradigm in which multiple
agents pursue shared objectives through local perception, information exchange, and coordinated action.
UAV swarms embody this paradigm by coordinating multiple vehicles in tasks such as search, inspection, and tracking. Recent advances in large
language model (LLM)
agents have strengthened natural-
language task understanding and high-level planning, providing a flexible semantic interface between mission descriptions and collective behavior. While these advances expand semantic
reasoning, applying LLM
agents to
UAV swarms raises challenges in grounding model decisions in executable capabilities, reconciling global task
reasoning with distributed execution, and using mission-specific experience for continual adaptation. To address these challenges, we introduce AeroWeaver, an
embodied-
agent harness that weaves individual
UAV skills into coordinated mission-level behavior. AeroWeaver connects semantic decisions to governed skills, organizes role-conditioned local
agents for distributed coordination, and uses role-indexed state-action-reward experience to refine skill selection online. Experiments and runtime validation show that AeroWeaver maintains valid skill execution under tested conditions and supports body-local multi-
UAV operation without a central
agent generating joint actions from global context, while reward-guided online updates provide a training-free path for adaptive learning swarm
agents from accumulated execution experience. Code: https://github.com/Admire-ljb/AeroWeaver.
Read the full abstract ▾
All authors Jiabin Lou, Yirong Yang, Haopeng Wang, Xuxin Lv, Xinyu Liu, Diyuan Hou, Xuehong Liu, Rongye Shi, Wenjun Wu
Artificial Intelligence
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
Youjia Wang, Lin Xu, Yang Sun et al. (+3 more)
Safety
alignment teaches large
language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when harmful intent is concealed within seemingly benign contexts. Robust safety therefore requires both knowledge of safety boundaries and vigilance: the ability to detect unusual premises, misleading
reasoning, and latent risks beneath surface-level semantics. Vigilance requires models to scrutinize a request's underlying intent and assumptions before acting. To cultivate this capability, we introduce cunning questions, which are not necessarily safety-related but contain misleading premises, atypical
reasoning, or subtle inconsistencies. We hypothesize that learning to look beyond such
reasoning traps can transfer to safety-critical scenarios. Experiments show that Cunning training improves robustness to out-of-distribution jailbreak attacks and strengthens subsequent safety fine-tuning. Furthermore, augmenting an existing state-of-the-art safety
alignment pipeline with Cunning establishes a new state of the art across our evaluated settings, reducing mean ASR across nine backbone–
benchmark combinations from 17.40% to 15.05%. Trace analysis after matched safety fine-tuning suggests that safety judgments are more likely to govern responses before harmful planning begins. A conditional theoretical analysis further characterizes when invariance learned from cunning data can transfer to safety-related inputs. These findings suggest that cunning data can strengthen model vigilance and complement conventional safety
alignment.
Read the full abstract ▾
All authors Youjia Wang, Lin Xu, Yang Sun, Yuxiao Lu, Chengfang Fang, Jie Shi
Artificial Intelligence · Cross-listed from cs.CR
MiST: Mid-Training LLMs for Cybersecurity
Oded Ovadia, Elad Ben Zaken, Elad Guttman et al. (+1 more)
Cybersecurity combines high-stakes analysis with complex technical
language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security
Transformer), a suite of 8B and 32B models that achieve strong performance on public cybersecurity
benchmarks. We use mid-training as an intermediate adaptation stage between general pre-training and cybersecurity training. Rather than performing continual pre-training over large volumes of raw domain text, we curate a compact, expert-vetted seed corpus, and transform it into high-quality domain-specific synthetic training data. The final MiST checkpoints improve mean cybersecurity accuracy by +13.1 and +8.6 absolute percentage points over the corresponding Qwen baselines for 8B and 32B, respectively, corresponding to relative gains of +27.0% and +15.8%. Ablation results further show that these cybersecurity gains arise in the mid-training and supervised fine-tuning stages through a combination of the synthetic data generation flows. Furthermore, we show that MiST provides a stronger initialization for downstream task-specific fine-tuning adaptation and reinforcement learning.
Read the full abstract ▾
All authors Oded Ovadia, Elad Ben Zaken, Elad Guttman, Orly Moreno Kadosh
Artificial Intelligence · Cross-listed from cs.RO
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Shijie Lian, Bin Yu, Zhaolong Shen et al. (+5 more)
Action tokenizers play a central role in autoregressive
vision-
language-action (VLA) models, determining both the targets for policy training and the executable commands recovered from predicted
tokens. Their fidelity is commonly evaluated using pointwise reconstruction metrics such as mean squared error (MSE), yet small individual errors do not fully characterize how faithfully action adjustments across demonstrations are preserved. After compression, similar actions may still cluster around a representative motion, while the adjustments needed for different contexts are diminished, distorted, or even reversed. We introduce physical rank consistency (PRC) to measure how well tokenization preserves local physical distance rankings after reconstruction. Evaluating decoded actions provides a common reference across
token vocabularies and decoder architectures, complementing pointwise accuracy with a measure of relational fidelity. We further present ActionPiece, which preserves physical action relationships through joint supervision of representation learning and quantization. Physical rank preservation supervises near-far ordering in encoder and quantized feature distances, while quantization regularization applies the same ordering to codeword assignment distributions. Both objectives augment reconstruction, producing discrete action
tokens for standard autoregressive policy learning and execution through a frozen decoder. Under the same Qwen3-VL-4B policy training setup, ActionPiece achieves 94.8% on LIBERO and 68.8% on unseen LIBERO-Plus, with additional evaluations reaching 71.9% on SimplerEnv and 51.5% across VLA-Arena L0-L2. Component ablations show that the two objectives jointly improve PRC and policy success, demonstrating the value of physical relationship supervision for action tokenization.
Read the full abstract ▾
All authors Shijie Lian, Bin Yu, Zhaolong Shen, Xiaopeng Lin, Yichao Du, Zhirui Zhang, Laurence T. Yang, Kai Chen
Artificial Intelligence
Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
Pietro Miotto, Lucia Mellini, Tommaso Marzi et al. (+5 more)
Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases, genes,
proteins, and patients. This hybrid structure raises the question of whether
hyperbolic embeddings, which naturally capture tree-like organization, remain useful beyond purely hierarchical graphs. We present a preliminary study of
hyperbolic graph representation learning for Mendelian-disease differential diagnosis on a patient-integrated biomedical graph. Experiments on isolated ontology subgraphs show that
hyperbolic models achieve strong performance in substantially lower dimensions than Euclidean baselines. We then evaluate the models on a link-prediction task that ranks candidate diseases for each patient. Results suggest that
hyperbolic embeddings can exploit biomedical hierarchical structure while supporting diagnostic
reasoning over heterogeneous patient-level graphs.
Read the full abstract ▾
All authors Pietro Miotto, Lucia Mellini, Tommaso Marzi, Cesare Alippi, Elena Casiraghi, Alberto Paccanaro, Giorgio Valentini, Mauricio Soto-Gomez
Artificial Intelligence
First Token Matters: Understanding Safety Collapse in Large Reasoning Models
Yizheng Yang, Haining Yu, Yuechen Wang et al. (+4 more)
Large
Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety
alignment often degrades when handling harmful queries. Existing approaches to improving safety largely rely on additional training or preference optimization, while offering limited understanding of the internal mechanisms behind safety failures. In this work, we investigate this failure through a
token-level positional analysis of refusal dynamics and identify a localized vulnerability at the onset of
reasoning, which we term Onset Refusal Collapse (ORC). We find that the refusal-related signal of LRMs drops sharply at the first generated
token under harmful queries, which is associated with unsafe response generation. Motivated by this finding, we propose SafeToken, a lightweight inference-time intervention that injects a learned continuous safety anchor precisely at
reasoning onset. Despite updating only a single
token embedding, SafeToken effectively mitigates ORC, improves safety on harmful-query
benchmarks, and largely preserves
reasoning utility. These results suggest that safety failures in LRMs can arise from a transient breakdown at the critical transition from understanding to generation.
Read the full abstract ▾
All authors Yizheng Yang, Haining Yu, Yuechen Wang, Yikai Hou, Xing Fu, Jinbo Yang, Tianqing Zhu
Artificial Intelligence · Cross-listed from cs.CV
CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models
Tianbin Liu, Jian Zhu, Taiyi Su et al. (+5 more)
FastWAM-style world action models enable efficient action-only inference, but generalize poorly under visual distribution shifts. Their reconstruction-oriented representations emphasize appearance-specific details, limiting generalization to unseen scenes and objects. Without observation history, the model also lacks temporal evidence for robustly identifying task-relevant state changes and motion in unfamiliar visual conditions. To address these limitations, we present the Causal Semantic World Action Model (CSWAM), which augments FastWAM with a causal semantic expert built on V-JEPA 2.1. V-JEPA provides temporally grounded representations of semantic state changes and motion with less dependence on appearance-specific details. The expert learns their future
evolution from a sparse history of current and past observations and shares the history-derived context with both the
video and action streams through causal
attention. At inference, CSWAM conditions action denoising on the current
video state and observed semantic history, retaining efficient action-only inference. We conduct simulation and real-
robot experiments to evaluate generalization under distribution shifts. With
embodied pretraining, CSWAM raises Randomized success on RoboTwin 2.0 Clean-to-Randomized transfer from 10.16% to 45.18%, a gain of 35.02 percentage points over FastWAM. Across two real-
robot tasks and three OOD difficulty levels, CSWAM improves average success over FastWAM by 42.5 percentage points, from 27.5% to 70.0%.
Read the full abstract ▾
All authors Tianbin Liu, Jian Zhu, Taiyi Su, Jianjun Zhang, Chong Ma, Zitai Huang, Weiyi Lu, Yi Xu
Artificial Intelligence
Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
Cai Ke, Xinghao Chen, Xiaoyu Shen et al. (+6 more)
Personalized
agents are required to reason over long-term history interactions to infer both explicit preferences and implicit behavioral evidence. While early flat
retrieval methods score
memory fragments independently and neglect the distributed information, current structured
memory frameworks rely on query-agnostic static graphs that fail to capture the context-dependent relations. Crucially, raw textual
memories are inherently entangled and noisy, making fine-grained personalization and cross-session
reasoning computationally prohibitive. To this end, we present LGM, a novel neuro-symbolic framework that shifts long-term
memory disentanglement into a continuous latent space. Specifically, (i) instead of persisting fixed graphs, we design a tailored latent graph construction with a sparse autoencoder. Subject to each query, it maps historical interactions into latent
memory nodes and disentangles the
memory traces into sparse concept activations, dynamically synthesizing query-aware relational edge weights. (ii) A graph encoder then treats the query
embedding as a conditioning preference to direct non-linear message passing across the task-specific latent subgraph. This yields a highly expressive
memory representation for effective activations. Extensive experiments on long-term personalization
benchmarks demonstrate that LGM significantly outperforms state-of-the-art baselines in capturing both explicit and implicit preferences while enabling personalized responses.
Read the full abstract ▾
All authors Cai Ke, Xinghao Chen, Xiaoyu Shen, Keyu Chen, Siyu An, Junnan Dong, Ruifeng Xu, Ruizhi Qiao, Xing Sun
Artificial Intelligence
Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
Xiangfan Wu, Zonghao Ying, Huiyu Wu et al. (+4 more)
How does a multi-
agent system evolve from a local deviation into collective loss of control? We propose an epidemic explanation organized around accidental mutation, contagion, and recovery. A spontaneous deviation creates a seed; communication enables other
agents to adopt and retransmit its unsafe strategy; collective failure can emerge when propagation outpaces correction and containment. Thus, rare individual deviations can coexist with substantial collective risk. Motivated by reported OpenAI
agent coordination incidents, we examine two ingredients of this mechanism. A deployment audit identifies implicit communication paths between nominally independent evaluation runs and verifies transport through a default Docker backend. RogueHandoff-20, a
benchmark of 20 executable scenarios, tests recipient susceptibility by injecting unsafe trajectories generated by a modified Qwen-27B route. Across four native-pending routes, executed harm is 0-5% on normal tasks and 40-95% after injection, exceeding paired direct malicious requests by 5-45 percentage points. These results support low observed baseline harm alongside high conditional susceptibility; they do not establish natural rare-event rates or demonstrate an autonomous cascade. The account motivates complementary defenses: strengthen resistance and recovery alongside prevention of spontaneous deviations, and audit and restrict unintended communication paths that can turn local failures into collective loss of control.
Read the full abstract ▾
All authors Xiangfan Wu, Zonghao Ying, Huiyu Wu, Xing Zheng, Huangsheng Cheng, Xiaorong Shi, Jing Guo
Artificial Intelligence
The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models
Jisoo Yang, Jaeho Han, Trung X. Pham et al. (+1 more)
A calibrated
Vision-
Language Model (VLM) can repeatedly self-correct, say "Wait, I should recheck," arrive at the wrong answer, and still report high confidence. We find that this occurs because verbalized confidence is largely trajectory-independent in the VLMs and calibration methods we evaluate. We examine this through three complementary lenses: content variation,
token masking, and the model's own hesitation markers. We show that confidence is insufficiently sensitive to what the
reasoning trajectory actually contains, and that calibration training can paradoxically worsen this disconnect. Since existing metrics like ECE and AUROC cannot detect this problem, we propose the Trajectory-Grounding Score (TGS) in two complementary forms: TGS-self, which compares confidence with and without access to the model's own trajectory, and TGS-pair, which tests whether the model assigns higher confidence to correct trajectories than to flawed ones along the
vision,
reasoning, and answer axes. We propose TGS-Bench, a model-agnostic suite spanning 10
benchmarks with controlled good/bad trajectory pairs, and show that conventional calibration rankings diverge from trajectory-grounding rankings, exposing a blind spot in current evaluation practice.
Read the full abstract ▾
All authors Jisoo Yang, Jaeho Han, Trung X. Pham, Junyeong Kim
Artificial Intelligence
Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving
Rongxiang Zeng, Linsen Cai, Jiafu Zhang et al. (+7 more)
Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We introduce RiskWorld, a risk-aware world modeling framework for shared occupancy
forecasting and selective trajectory replacement. Spatial risk fields and temporal actor context are fused with visual bird's-eye-view features. Flow-guided
evolution transports occupancy and scene features, while signed residuals correct occupancy after transport. One forecast is generated per planning step and reused across candidates. Each candidate is compared with a current-state persistence reference, yielding a nonnegative collision-score correction. The trajectory selected by current-world evaluation serves as the planning anchor and is replaced only when additional predicted risk triggers intervention and an alternative satisfies component-wise constraints on predicted risk and trajectory error. Candidate geometries remain unchanged. We evaluate RiskWorld for open-loop planning on nuScenes using camera features, annotation-derived current and historical actor states, and
dataset-provided map context. RiskWorld achieves the lowest collision rate at a long evaluation horizon of 3 s, and the second-best average L2 error among various state-of-the-art baselines, while running at 11.5 FPS on a single NVIDIA RTX 4090 with 90.81 M parameters. Within-setting ablations show that RiskWorld achieves lower collision rates than the current-state rescoring baseline, while forecast reuse enables additional candidates to be evaluated at low marginal computational cost.
Read the full abstract ▾
All authors Rongxiang Zeng, Linsen Cai, Jiafu Zhang, Yijie Zhong, Yide Tao, Shuai Wang, Nan Zheng, Hai L. Vu, Alvaro Garcia Hernandez, Yongqi Dong
Artificial Intelligence · Cross-listed from econ.GN
Multitask Reinforcement Learning for Assisting Choice Model Specification
Gabriel Nova, Stephane Hess and Sander Van Cranenburgh
Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and behavioural plausibility. We present Delphos, a multitask reinforcement learning framework that learns transferable specification strategies across transport choice
datasets. Delphos frames model specification as a sequential decision-making problem in which it applies a sequence of modelling actions and receives feedback from an estimation environment based on model performance and convergence. To transfer modelling decisions across
datasets with different sets of variables, Delphos represents utility specifications as sets of modelling terms using a DeepSet-Q architecture, allowing a shared specification policy to learn across multiple
datasets. Trained on nine transport choice
datasets, Delphos consistently outperforms independently trained single-task
agents, indicating that sharing modelling experience improves learning efficiency and helps identify promising sequences of modelling decisions with fewer unsuccessful estimation attempts. When applied without further training to the unseen Swissmetro and Decisions
datasets, the same
agent identifies competitive specifications in less than 20 minutes on a standard CPU. It achieves a higher log-likelihood per observation than the VNS metaheuristic on Swissmetro and performance comparable to a published MNL specification developed by expert modellers on Decisions. These findings show that accumulating and reusing modelling experience enables Delphos to function as an intelligent assistant for discrete choice model specification. It reduces manual trial-and-error while allowing modellers to retain control over model diagnosis, refinement, and final selection.
Read the full abstract ▾
Artificial Intelligence
WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories
Yuna Oikawa, Kei Endo, Takanori Uzawa et al. (+5 more)
Automating biological research requires general-purpose, reproducible
robot systems that allow individual wet-lab researchers to delegate
robot tasks without performing teleoperation or neural-network training.
Vision-
language-action policies have been proposed for general-purpose arms, but can lose performance when their operating environment changes. We therefore built WetRobo, a
robot kit that can readily transfer between laboratories. It consists of one
robot arm, laboratory equipment (an incubator, a reagent bottle with a cap, and a Petri dish), the existing code that moves the arm, teleoperation demonstrations of each task that we recorded, and a general
AGENTS.md skill file. A biological experimentalist provides natural-
language tasks without collecting local teleoperation training data or training a neural network. The coding
agent observes the local laboratory and writes and executes programs, using external tools as needed for adaptation. We demonstrate use of WetRobo with OpenAI Codex (gpt-5.6-sol) on three successful tasks: lifting a Petri dish lid, removing a bottle cap, and opening the incubator door, all in real-world laboratories. The coding
agent achieved the cap task in both laboratories, Lab X and Lab Y, whereas a VLA fine-tuned on Lab X demonstrations succeeded there but failed to transfer to Lab Y. These results point to a practical route for laboratory robotics: instead of training a policy for each laboratory, distribute a kit and let a coding
agent adapt it in each laboratory. Code, demonstrations, and the evolved programs are available at https://github.com/tsudalab/WetRobo.
Read the full abstract ▾
All authors Yuna Oikawa, Kei Endo, Takanori Uzawa, Yunzhe Zhang, Manan Anjaria, Lerrel Pinto, Sherry Yang, Koji Tsuda
Artificial Intelligence
HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition
Kamilia Zaripova, Nassir Navab, Azade Farshad et al. (+1 more)
More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet diagnosis remains difficult because patients initially present with incomplete and heterogeneous phenotypes. We present HPOQuest, a training-free framework for sequential phenotype acquisition in rare-disease diagnosis. Starting from a small set of observed patient phenotypes, HPOQuest maintains a probabilistic disease ranking and iteratively selects informative follow-up questions to support clinicians during patient assessment. Confirmed phenotypes update the disease ranking, while all responses update the candidate question set. Across four
benchmark cohorts, HPOQuest substantially improves diagnosis from sparse initial phenotypes, with gains of up to 30% points at Recall@1 and 45% points at Recall@5. These results demonstrate that sequential phenotype acquisition can substantially improve rare-disease diagnosis from limited initial clinical evidence.
Read the full abstract ▾
All authors Kamilia Zaripova, Nassir Navab, Azade Farshad, Annalisa Marsico
Artificial Intelligence · Cross-listed from cs.LG
TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
Shunya Nagashima and Yuta Funayama
Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight
memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza
benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the
memory itself.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
A Non-Linear Neuron Based Detection of Isolated Pixels in Binary and Grayscale Images using Contrast Sensitive Receptive Fields
Nassir Mohammad
Identifying isolated points is important in image processing applications such as medical imaging, astronomy and quality control management. Other domains, such as cybersecurity, also present challenges that can be framed as image processing problems. One example of particular interest is the identification of anomalous single nodes in spatially organised networks where groups of nodes in different regions share similar feature values. This task can involve both binary and more complex grayscale images. However, existing methods face limitations: template matching is infeasible for grayscale images, while 2nd order derivative based methods are highly sensitive to noise and require user-specified thresholds. To overcome these issues, a novel method is proposed for detecting meaningful single-pixel deviations in images. This approach modifies and extends a
neuron model, originally designed for anomaly detection, to operate on spatially diameter limited receptive fields that incorporate excitatory and inhibitory regions. The result is a method that is free from user-specified thresholds and parameters, and can be applied to both binary and grayscale images, providing an effective, robust and efficient solution.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
Jens U. Brandt, Noah C. Puetz, Alexander Windmann et al. (+4 more)
Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail, learning-based predictors can produce physically implausible estimates that propagate to system-level failures. We argue that real-world deployment demands robustness and introduce MuViS-C, the first multi-domain
benchmark of robustness against common sensor failures in learning-based virtual sensing. Building on an existing nominal-performance
benchmark and established corruption taxonomies, it covers ten sensor failure modes, from subtle drifts to catastrophic signal dropouts, at multiple severities. These are paired with complementary robustness measures capturing average error under corruption, relative degradation, and worst-case fragility. Across nine
datasets from six domains, we
benchmark six architectures spanning gradient-boosted trees and the major inductive biases for sequence modeling: convolution, recurrence,
attention, and MLP-mixing. On the
attention-based architecture, we further probe three robustification strategies. We find that (i) every model degrades substantially under corruption, becoming worse than a naïve predictor on at least one corruption setting, (ii) gradient-boosted tree ensembles achieve strong robustness, and (iii) dedicated robustification closes the gap between the
attention-based architecture and the most robust models, though each strategy hurts nominal performance. The
benchmark's multi-domain design proves essential, as model rankings shift across
datasets, and no single domain captures the full robustness picture. MuViS-C is open-source and extensible to new
datasets, failure modes, measures, and models.
Read the full abstract ▾
All authors Jens U. Brandt, Noah C. Puetz, Alexander Windmann, Marc Hilbert, Elena Raponi, Thomas Bäck, Thomas Bartz-Beielstein
Artificial Intelligence
Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland
Otto Segersven and Pentti Henttonen
We report the results of a Turing Test conducted in Finland in the Finnish
language. Because
languages and cultural contexts are unevenly represented in LLM training data, we expected the model (ChatGPT 5.2) to perform worse in a Finnish-
language Turing Test than in previously studied English-
language US contexts. We also present model-generated role prompting as a replicable technique for conducting comparative LLM-based Turing Tests designed to improve construct validity. Contrary to our expectations, the LLM passed the Finnish Turing Test. A prominent source of error was participants' reliance on linguistic cues, particularly colloquial Finnish, as markers of human authorship. We reframe the Turing Test from a test of intelligence to a comparative method for examining whether an AI system can display credible membership in a particular social world. Because its outcome reflects model capabilities, prompted identity, insider competence among human participants, and their AI literacy, the method provides a useful probe of the human-machine boundary across domains.
Read the full abstract ▾