SocialReasonBench is a new video‑multiple‑choice QA benchmark designed to test socially grounded reasoning in interactive narrative videos. It uses branching gameplay footage from *Detroit: Become Human*, where player choices create alternative social outcomes that can be verified against the game’s script and flowchart. The benchmark includes seven reasoning dimensions—such as intent recognition, emotional empathy, moral dilemma, counterfactual reasoning, and causal antecedent—and employs a multi‑agent pipeline to curate clips, ground answer labels, and generate theory‑guided questions with diagnostic distractors.
By Zheyu Huang, Zijing Shi, Haozhe Luo, Huadong Tang, Mingyu Liu, Meng Fang, Ling Chen
SkillForge is a framework that breaks down formal code synthesis into reusable atomic skills, each handling a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or repair. A verification-driven harness coordinates these skills by submitting candidates to the Dafny verifier, diagnosing failures, and routing them deterministically to the appropriate repair skill until correctness is achieved or a budget is reached. On a curated benchmark, SkillForge outperforms state‑of‑the‑art agentic and iterative baselines, requiring fewer tokens and lower latency, with ablation studies showing each skill’s measurable contribution and rapid convergence.
By Yanming Liu, Xinyue Peng, Jiannan Cao, Xinyi Wang, Jinbo Su
QueryGraph is a system that transforms natural language queries into structured graphs for reliable multi-tool execution. It employs a deterministic planner that uses depth-first search to resolve tool dependencies and combine results, improving reliability over traditional keyword searches. The approach works well even with smaller or locally hosted large language models, achieving high accuracy in multi-step, cross-tool queries.
By Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng Chau
The paper introduces Uncertainty-Driven Replay Memory (UDRM), a new experience replay buffer for reinforcement learning that prioritizes storing transitions with high uncertainty estimates. Unlike traditional buffers that rely on temporal difference error or transition distributions, UDRM updates its contents based on uncertainty derived from the RL model during training. Experiments show that this uncertainty-aware buffer leads to higher rewards during training compared to other uncertainty-aware RL frameworks.
By Sheeraja Rajakrishnan, Alexander G. Ororbia, Travis Desell, Daniel E. Krutz
The paper introduces TrustFlip, an attack that exploits consistency‑based defenses in vehicular collaborative perception by deploying physical adversarial objects to create inconsistent observations among benign vehicles. This misattribution lowers the trust score of a targeted vehicle, leading to its exclusion from the collaboration and a degradation of perception performance. The authors evaluate the attack across multiple architectures, showing it can remove a benign vehicle in up to 87.7% of scenarios and reduce Average Precision by up to 13%, and propose a mitigation called TrustReflect that reduces the attack success rate by 35–100%.
By Yutong Liu, Chenyi Wang, Ming F. Li, Qingzhao Zhang
Unified-MAS is a two-stage framework that decouples node implementation from orchestration in Automatic Multi-Agent Systems. It first searches external knowledge to synthesize domain‑specific node blueprints, then uses a perplexity‑guided reward to optimize bottleneck nodes. Experiments across four specialized domains show that adding Unified-MAS to existing baselines improves performance‑cost trade‑offs by up to 14.2% while lowering costs.
By Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin
arXiv:2606.22394v3 Announce Type: replace
Abstract: Consistency distillation has significantly accelerated diffusion-model inference, but its sampling dynamics remain underexplored. We reveal an asym...
By Songtao Tian, Guhan Chen, Bohan Li, Jingyi Ma, Zixiong Yu
arXiv:2606.08684v2 Announce Type: replace
Abstract: We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive ana...
By George Ling, Lijin Yang, Hao Yang, Zhongzhan Huang
arXiv:2511.22187v4 Announce Type: replace
Abstract: Realistic and controllable simulation is critical for advancing end-to-end autonomous driving, yet existing approaches often struggle to support no...
By Qiang Li, Yingwenqi Jiang, Tuoxi Li, Duyu Chen, Xiang Feng, Yucheng Ao, Shangyue Liu, Xingchen Yu, Youcheng Cai, Yumeng Liu, Yuexin Ma, Xin Hu, Li Liu, Yu Zhang, Linkun Xu, Bingtao Gao, Xueyuan Wang, Shuchang Zhou, Xianming Liu, Ligang Liu
arXiv:2608.28794v1 Announce Type: cross
Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs...
By Benjamin Fehrensen, Jens Hubler
arXiv:2608.28708v1 Announce Type: cross
Abstract: Prospective silent trials provide an important bridge between retrospective validation of artificial intelligence (AI) models and their use in clinic...
By Gabriele Campanella, Matthew Croken, Olga Lukatskaya, Jane Houldsworth, Ricky Kwan, Peter Sch\"uffler, Chad Vanderbilt
arXiv:2608.30839v1 Announce Type: new
Abstract: Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose i...
By Xiaopei Zhu, Siyuan Huang, Zhanhao Hu, Jianmin Li, Jun Zhu, Xiaolin Hu
arXiv:2601.16690v2 Announce Type: replace
Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather tha...
By Xinze Li, Ziyue Zhu, Siyuan Liu, Yubo Ma, Yuhang Zang, Yixin Cao, Aixin Sun
arXiv:2508.14323v3 Announce Type: replace
Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none...
By Yixin Chen, Ying Xiong, Shangyu Wu, Yufei Cui, Xue Liu, Nan Guan, Chun Jason Xue
arXiv:2608.31128v1 Announce Type: new
Abstract: Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and ci...
By Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu, Hsin-Ling Hsu, Donghua Zhang, Chenwei Wu, Jun-En Ding, Tongze Zhang, Shihao Yang, Pengfei Hu, Fang-Ming Hung, Feng Liu
arXiv:2608.29241v1 Announce Type: new
Abstract: Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a casca...
By Zachary Ellis, Spencer Hazel, Adam Brandt, Yajie Vera He, Ernest Lim, Jared Joselowitz
arXiv:2608.29133v1 Announce Type: new
Abstract: History is not preserved in complete, continuous form. Accounts of a person's activities, relationships and historical contexts are scattered across te...
By Yifeng Lu, Zijie Yang, Jie Li, Qingkai Min, Yue Zhang
arXiv:2605.08211v2 Announce Type: replace-cross
Abstract: Channel-gain maps provide the channel gain between any two locations in a geographical region. They find numerous applications, from resource...
By Prasenjit Dhara, Daniel Romero
arXiv:2310.04363v3 Announce Type: replace
Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits t...
By Edward J. Hu, Moksh Jain, Eric Elmoznino, Younesse Kaddar, Guillaume Lajoie, Yoshua Bengio, Esmeralda S. Whitammer
arXiv:2310.02423v3 Announce Type: replace
Abstract: We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\D...
By Jean-Pierre Falet, Hae Beom Lee, Esmeralda S. Whitammer, Chen Sun, Dragos Secrieru, Thomas Jiralerspong, Dinghuai Zhang, Guillaume Lajoie, Yoshua Bengio