2 papers
cs.AI2026
When to Forget: Risk-Controlled Context Adaptation for Long-Horizon Agents
Chenle Chen, Yangbo Wei, Zhijie Zheng +6
Long-horizon agents learn from failure, but the value of a failure record can change as execution progresses. We study when retaining, compressing, or removing the same history blo…
cs.DC2026
Serve Now or Improve Later? Scheduling Self-Evolution in Online Agent Systems
Yangbo Wei, Junhong Qian, Zhen Huang +6
Online agents can improve future service by constructing reusable tools, guidance, or model states, but this work competes with current requests for the same GPUs. Exploiting idle…