1 citations · 1 across the 16 of their papers we have counts for
17 papers
MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
Jingxuan Wu, Yuzhe Yang, Yiqiao Huang +6
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which preferences still hold, which were revised, and which constraints a…
Probing the Misaligned Thinking Process of Language Models
Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2
Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-sta…
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu +14
Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stal…
Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy
Xu Shen, Zhen Tan, Song Wang +4
Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual…
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13
Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusabl…
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a c…
Stateful Reasoning via Insight Replay
Bin Lei, Caiwen Ding, Jiachen Yang +2
Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monoton…
EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
Gurusha Juneja, Dylan Lu, Saaket Agashe +7
Theory of Mind (ToM), the ability to track others epistemic state, makes humans efficient collaborators. AI agents need the same capacity in multi agent settings, yet existing benc…
BoolXLLM: LLM-Assisted Explainability for Boolean Models
Du Cheng, Serdar Kadioglu, Xin Wang
Interpretable machine learning aims to provide transparent models whose decision-making processes can be readily understood by humans. Recent advances in rule-based approaches, suc…
Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
Yilin Zhang, Yingkai Hua, Chunyu Wei +2
Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either det…
Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
Zihan Huang, Junda Wu, Tong Yu +6
While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliability. Consolidating agent co…
How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
Zhiyuan Zhai, Xinkai You, Wenjing Yan +1
Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces r…
SafePro: Evaluating the Safety of Professional-Level AI Agents
Kaiwen Zhou, Shreedhar Jangam, Ashwin Nagarajan +7
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in vari…
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Chengzhi Liu, Zhongxing Xu, Qingyue Wei +5
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. Howe…
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
Kaiwen Zhou, Xuandong Zhao, Gaowen Liu +4
Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose…
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao +5
The rapid development of large reasoning models (LRMs), such as OpenAI-o3 and DeepSeek-R1, has led to significant improvements in complex reasoning over non-reasoning large languag…
Multimodal Situational Safety
Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao +3
Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments.…