Learning Agent-Compatible Context Management for Long-Horizon Tasks 事件

Learning Agent-Compatible Context Management for Long-Horizon Tasks arXiv:2605.30785v1 Announce Type: new Abstract: LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and reasoning failures. Prior work mitigates this through context management with agent-side context control or fixed strategies such as summarization, which require training the agent itself for adaptation -