腾讯推出ContextPilot智能体，能自主管理上下文、规划全局任务，比现有方法更高效地处理长距离任务。
腾讯训练智能体管理自身工作上下文，在上下文编辑层面分配信用。长距离任务迫使模型检索、整合和维持多轮对话中的分散信息，保持所有交互历史会使工作上下文无限增长。ContextPilot添加全局规划、长期记忆和自适应软压缩功能，使智能体能卸载信息而非仅丢弃信息。在长上下文问答和深度搜索任务上，ContextPilot在多个基础模型上超越现有基线，同时保持更紧凑的工作上下文。
Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assi...
Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, integrate and maintain scattered information across many turns, and keeping every interaction history makes the working context grow without bound. Recent proactive methods let a model edit its own context with tools, but the toolset stops at search, deletion and summarization. ContextPilot adds global planning, long-term memory and adaptive soft compression, so the agent can offload information rather than only discard it. The training side is where it gets interesting. Standard RL hands the final trajectory reward to every intermediate edit equally. ContextPilot uses context and entropy variation to find which editing decisions actually mattered, samples branches at those points, and estimates action-level advantages from all branched trajectories passing through that edit. On long-context QA and deep search it beats existing baselines across several base models while holding a more compact working context. Code is available. Paper: arxiv.org/abs/2608.28476 Chat with Paper: academy.dair.ai/papers/context… 💬 7 🔄 2 ❤️ 17 👀 2238 📊 10 ⚡