返回首页
arXiv AI··论文与技术

ClawLoop: Self-Improving Agents via Harness-Native Training Loop

中文摘要

ClawLoop 为 harness 环境下的 LLM 智能体引入了自我提升训练循环,使其能通过原生迭代实现进化,减少对外部教师模型的依赖。

English Summary

ClawLoop introduces a self-improving training loop for LLM agents in harness environments, enabling autonomous evolution and reducing reliance on external teacher models.

原文节选

arXiv:2610.14118v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both…