3 papers
cs.AI2026
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Zefeng Wang, Minxi Yan, Jinhe Bi +3
Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. Howe…
cs.AI2026
DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning
Tingxin Yang, Zefeng Wang, Mengyue Wang +4
Test-time scaling improves large language model reasoning, but spends compute uniformly along a reasoning trace, even in stretches that are already stable. Motivated by the observa…
cs.CV2024
Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
Zefeng Wang, Zhen Han, Shuo Chen +6
Multimodal LLMs (MLLMs) with a great ability of text and image understanding have received great attention. To achieve better reasoning with MLLMs, Chain-of-Thought (CoT) reasoning…