Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
中文摘要
该研究提出了一种新型自我进化框架,使AI智能体能通过自我优化来提升多任务处理能力,摆脱了对外部人工设计及其特定基准的依赖。
English Summary
This study introduces a framework for AI agents to self-evolve and optimize their operational harnesses across multiple tasks, reducing reliance on manual design and task-specific constraints.
arXiv:2609.38372v1 Announce Type: new Abstract: A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has begun to let agents improve their own harnesses, a line of work known as self-evolving harnesses. In most existing methods, a separate proposer running on a human-designed harness modifies the solver's harness, and a separate harness is evolved for each benchmark. Real-world tasks come from many domains, so both the evolution and the evaluation of a harness should cover a diverse range of tasks. We propose a framework close to recursive self-improvement: the same frozen model, on the same version of the harness, first solves tasks as the solver and then, as the proposer, reads the complete run records and directly edits the harness that runs it. Each evolution batch draws tasks from five benchmarks in different domains. To measure generalization, training and held-out tasks are strictly separated, and we additionally evaluate on five out-of-distribution benchmarks never used during evolution. We frame the evolution process as deep-learning training with two stages, m…