SOURCE-LINKED INTELLIGENCE

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions, but preserving all interaction histories leads to a continuously growing working context. Recent proactive context management methods allow models to edit their own working context with specialized tools, yet they still face three key limitations: (1) a limited toolset restricted to search, deletion, and summarization, with no support for global planning, long-term memory, and adaptive compression; (2) inefficient exploration tha

Read original source ↗ Open in workspace

recordType

paper

region

Global