3 papers
cs.CR2026
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
Chao Yao, Yangbo Wei, Zhen Huang +5
Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache. Yet t…
cs.AI2026
Competence, Not Accuracy: A Diagnostic for Reference-Free Judge Gates in Skill Optimization
Chenle Chen, Yangbo Wei, Chao Yao +4
Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document, accepting each candidate through a validation gate. Existing gates rely on verifi…
cs.AI2026
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Yangbo Wei, Zhen Huang, Shaoqiang Lu +4
Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution frameworks typically assume a fi…