16 papers
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…