The paper introduces an adversarial reinforcement learning framework that learns the sparsest Denial-of-Service (DoS) attack schedule capable of destabilizing self‑triggered reinforcement learning controllers (RL‑STC). It proves a lower bound on the minimum number of jamming actions needed to force a crash and demonstrates that the learned adversary consistently defeats four different defenders—one LQR and three RL‑STC—across Pendulum, CartPole, and Quadrotor2D environments, outperforming greedy and periodic baselines in jam‑time‑per‑failure. The study also shows that the adversary remains effective under Gaussian observation noise and limited state information.
By Adam Haroon, Erick J. Rodr\'iguez-Seda, Tristan Schuler, Cody Fleming
The paper introduces CLAW, a method that uses a hypernetwork to generate low‑rank adapters for world models during test time, enabling efficient adaptation to new environments with only a few episodes of interaction. By jointly pretraining the hypernetwork and base model on simulated adaptations, CLAW balances computational efficiency and expressivity, outperforming both in‑context learning and gradient‑based adaptation in locomotion and manipulation tasks. The approach also mitigates overfitting in data‑scarce regimes and demonstrates that the benefit stems from expressive adapters rather than context conditioning.
By Fernando Palafox, David Fridovich-Keil
arXiv:2504. 07133v2 Announce Type: replace-cross Abstract: We revisit the problem of estimating $k$ linear regressors with self-selection bias in $d$ dimensions with the maximum selection criterion, as introduced by Cherapanamjeri, Daskalakis, Ilyas, and Zampetakis [CDIZ23, STOC'23].
By Alkis Kalavasis, Anay Mehrotra, Felix Zhou
The paper introduces Tasks over Application Manuals (TAM), a benchmark designed to test long‑horizon procedural reasoning in large language models. TAM uses real‑world tasks from ICD‑10‑CM clinical coding and U.S. federal sentencing, requiring models to follow extensive, rule‑based manuals and perform interdependent steps to produce exact answers. Experiments with GPT‑5 and various prompting strategies show very low exact‑match accuracy—1% for coding and 15.5% for sentencing—highlighting a gap between current benchmarks and the ability to reliably follow complex procedures.
By Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie, Sachin Chandrasekhar, Eugene Wen
The study investigates how deictic ambiguity—specifically the shifting reference of expressions like "previous"—affects Draft‑Verify‑Revise pipelines that use multiple large language models (LLMs). Using a synthetic dataset of 10 base examples and 21 reasoning‑effort configurations, six LLMs were evaluated for their ability to correctly resolve the ambiguous expression across the draft, verify, and revise stages. Results show wide variance in balanced accuracy, with GPT‑5.2 improving from 0.156 to 0.942 with increased reasoning effort, while Gemini 3 Pro consistently achieved high accuracy above 0.94 even at low reasoning effort, and meta‑evaluators often relied on surface cues when making errors.
By Obinna I. Ekekezie
The paper introduces UrduFactBench and UrduFactQA, two hand‑annotated benchmarks for claim verification and factual consistency evaluation in Urdu, created through a multi‑stage annotation process with native speakers. It also presents UrduFactCheck, a modular fact‑checking framework that uses both monolingual and translation‑based evidence retrieval to address the scarcity of high‑quality Urdu evidence. Experiments on twelve LLMs show that translation‑augmented pipelines outperform monolingual ones, highlighting ongoing challenges for open‑source models in Urdu.
By Sarfraz Ahmad, Hasan Iqbal, Momina Ahsan, Numaan Naeem, Muhammad Ahsan Riaz Khan, Arham Riaz, Muhammad Arslan Manzoor, Yuxia Wang, Preslav Nakov
DementiaCare-Bench is a new video benchmark designed to evaluate video-language models (VLMs) on understanding behavioral and psychological symptoms of dementia (BPSD). It contains 56 caregiver training videos, 94 clips across nine BPSD categories, and 2023 questions that are grounded in transcript spans and labeled by their visual demand. The benchmark reveals that most VLMs perform well on questions answerable by language alone but struggle with those requiring ordered frames, and a lightweight LoRA fine‑tune (DemCare‑VLM) can improve video dependence.
By Afrouz Sheikholeslami, Yuankai Qi, Xuyun Zhang, Luping Zhou, Amin Beheshti, Quan Z. Sheng, Ming-Hsuan Yang
PhysPlan is a training‑free guidance framework that enhances video diffusion models by incorporating physical awareness through agentic physics simulation. It uses a vision‑language model to generate a Chain‑of‑Visual‑Thought representation of kinematic trajectories and 3D depth, which then drives an object‑centric test‑time optimization that isolates kinematic changes and locks the passive environment. The framework also employs Kinetic Intensity Profiling to adapt hyperparameters to varying physical deformations, and demonstrates superior performance on PhyGenBench and Physics‑IQ benchmarks compared to existing VDM baselines.
By Minh-Loi Nguyen, Xuan-Vu Le, Thanh-Toan Do, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
AnchorVLN is an open‑vocabulary vision‑language navigation system that separates semantic proposals from geometric metrics. It uses a VLM to generate semantics while a geometry module supplies reliable metric quantities such as range and bearing, all within a Model Context Protocol server. The system achieves 64.4% on instruction following and improves object‑reference accuracy, reducing median center error from 3.37 m to 2.48 m.
By Long Giang Vu, Chengkai Yao, Yuxin Liu, FNU Aryan, Rajath Chandrashekar Aralikatti
The study examines how proactive in‑cabin agents should communicate in fully automated vehicles, comparing an event‑triggered policy that speaks at every event with a context‑sensitive policy that chooses Immediate, Delayed, or Silent responses. In a VR simulation with 41 participants, the context‑sensitive approach improved communication appropriateness and significantly lowered perceived interruptions, while trust levels remained unchanged. The results emphasize that event consequence, passenger activity, ongoing information value, and the need for confirmation should guide selective in‑cabin communication.
By Kaiser Hamid, Peihang Li, Nade Liang
VertexCBF is a framework that learns neural control barrier functions (CBFs) by approximating the stationary Hamilton–Jacobi value function with a neural network trained through physics‑informed and sparsely supervised learning. It exploits control‑affine dynamics and a convex polytope control set to generate supervision points via GPU‑parallel vertex‑restricted tree search, ensuring the learned CBF never exceeds the specified constraint function. The method was evaluated on 15 systems, outperforming baselines by recovering larger safe sets, and demonstrated on a mobile robot that safely avoids pedestrians using a neural CBF trained with this approach.
By Bojan Deraji\'c, Sebastian Bernhard, Wolfgang H\"onig
The paper introduces BQ-LoRA, a low‑rank adaptation framework for large language model agents that consolidates multiple LoRA adapters into a single one. It uses a behavior quotient manifold to balance trajectory updates and a decision‑preserving compression module to keep updates within a fixed rank budget while minimizing distortion of decision distributions. Experiments on AppWorld and BrowseComp‑Plus demonstrate that BQ‑LoRA outperforms standard LoRA and other low‑rank methods, with ablations confirming the benefits of both components.
By Pengyang Zhou, Xiaobin Tu, Zhengxi Liu, Rongkun Xue, Haochen Li, Miancan Liu, Ziyuan Chen, Yinggui Wang, Jinkui Ren, Xiantao Zhang
The paper introduces a reinforcement learning framework that uses groupoids to model local, state-dependent symmetries, allowing agents to discover equivalence structures during interaction. By maintaining orbit representatives and transporters that map raw states to canonical forms, learning and decision-making occur in a symmetry-reduced space while preserving local distinctions. Experiments show that this approach improves sample efficiency and convergence in dense, large-scale environments with partial symmetries, outperforming standard Q‑learning.
By Ben Opperman, Eduardo Alonso, Esther Mondrag\'on
The paper presents a curriculum‑based adversarial heterogeneous agent reinforcement learning (HARL‑AC) approach for autonomous quad‑copter landing on a ship deck in maritime settings. Using Heterogeneous‑Agent Proximal Policy Optimization (HAPPO) in NVIDIA Isaac Lab, the authors train a cooperative control policy that outperforms domain‑randomized baselines, achieving up to 97.5% success on in‑distribution sea states and higher median success and lower crash rates on out‑of‑distribution sea states. The adversarially trained policy also exhibits more cautious behavior, slightly increasing timeouts but improving safety in severe, unseen conditions.
By Allan Minh-Tam Nguyen, Sree Showrya Kotala, Stefan Banioi-Crijman, Kurt Driessens, Rico M\"ockel
The paper introduces a new criticality metric specifically designed for vulnerable road users (VRUs) and a scenario‑independent prediction framework that applies to all traffic participants. The VRU‑centric metric improves pedestrian criticality classification by up to 50 %, while the prediction framework surpasses state‑of‑the‑art metrics by 275 %, achieving an F1‑score of 0.96 on the DeepAccident dataset. These advances enable more accurate, scenario‑agnostic safety assessments for autonomous driving systems.
By J\"org Gamerdinger, Victor Schwarzenberger, Philipp Schmid, Sven Teufel, Oliver Bringmann
The article presents the first demonstration of an agentic TCAD calibration workflow for a fabricated bottom‑gate In–W–O transistor. Starting from measured transfer curves, the workflow uses measurement–TCAD residuals and local sensitivity tests to guide parameter corrections or additional physical models, accepting only updates that improve device metrics. For a 2%‑W reference device, five agent‑suggested updates reduced the multi‑metric device objective by 14.3× and achieved low errors in threshold voltage and on‑current across varying bias and geometry, showing model transferability and process sensitivity.
By Gyujun Jeong, Junmo Lee, Sungwon Cho, Woohyun Hwang, Kwangyou Seo, Suhwan Lim, Wanki Kim, Daewon Ha, Rishi Ranade, Kihang Youn, Ram Cherukuri, Yiyi Wang, Asif Khan, Shimeng Yu
GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.
By Umesh Bodhwani, Thanh Tran, Kai Wei
The paper introduces Affective Agent, a three‑layer reference architecture designed for on‑device personalized intervention reasoning in wearable systems. It integrates a compact sub‑billion‑parameter language model with physiological data, context, and user history to determine when and how to intervene, all without cloud support or per‑user retraining. The architecture’s perception, personalization, and reasoning layers adapt through host‑managed structured memory evolution, and evaluation on simulated indoor environmental quality scenarios shows that memory‑driven personalization and two‑pass reasoning enhance intervention decisions.
By Reina Mun, Zishen Wan, Vijay Janapa Reddi
The paper introduces a multi-vehicle dataset that includes camera, LiDAR, and radar sensor data along with scanned 3D models of all vehicles. Each vehicle’s pose and continuous kinematics are provided via RTK‑GNSS, enabling precise knowledge of the dynamic surroundings at any time. The dataset supports single‑ and multi‑object recordings with seven target vehicles, allowing evaluation of measurement effects such as occlusion and reflections thanks to known vehicle surface normals.
By Philipp Berthold, Bianca Forkel, Mirko Maehlisch
The paper introduces a bio‑inspired deep learning framework that models olfactory perception of complex chemical mixtures. It constructs neural response curves for molecule‑receptor interactions, fuses attention‑weighted multi‑receptor and concentration‑dependent multi‑molecule data, and transfers knowledge from molecular associations to improve mixture recognition. The model achieves 92.2% accuracy and offers a generalizable computational pathway from chemical blending to perceptual formation.
By Fei Wang, Xiaoya Xie, Junfei Liu, Huihao Wang, Yixiao Wang, Yintao Wang, Yi Li, Hao Dong, Xing Chen