PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
- 类型：arxiv
- 标识：2608.26530
- 链接：https://arxiv.org/abs/2608.26530
- 主分类：agent
- 形态：method
- 被引：2
- 被引来源：Semantic Scholar
- S2被引：2
- OpenAlex被引：0
- 影响力被引：0
- TLDR：PILOT is presented, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-evolution distils procedures and failure modes revealed during execution into reusable skills and memory.
- OpenAlex ID：W7204601596
- OpenAlex DOI：10.48550/arxiv.2608.26530
- DOI：10.48550/arxiv.2608.26530
- DOI来源：OpenAlex
- 开放获取：green
- 开放获取链接：https://arxiv.org/pdf/2608.26530
- OpenAlex更新：2026-09-04
- 待LLM分类：否
- 标题中文：PILOT in the Loop：面向长时序 Agent 的实时自我改进。
- TLDR中文：本文提出 PILOT，一种通过两种耦合机制实现实时自我改进的 supervisor-worker 框架：(1) live steering 允许独立的 supervisor 在执行期间重定向或中止当前 worker；(2) live self-evolution 将执行中发现的过程与失败模式提炼为可复用的 skills 与记忆。
- 来源文件：
- /inbox/tom/_candidates/2026-08-28-agent-rag-longcontext-candidates.json
- /inbox/tom/_candidates/2026-08-29-agent-rag-longcontext-candidates.json
- /inbox/tom/_candidates/2026-08-30-agent-rag-longcontext-candidates.json
- [S2 enrich]
- /inbox/tom/_candidates/2026-08-31-agent-rag-longcontext-candidates.json
- /inbox/tom/_candidates/2026-08-31-agent-memory-tool-use-candidates.json
- [OpenAlex backfill]