2 papers
cs.AI2026
MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory
Beidi Zhao, Yaoqi Chen, Yuru Feng +10
Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence buried far bac…
cs.AI2026
SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation
Yuru Feng, Yaoqi Chen, Beidi Zhao +7
Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-world deployments thus requir…