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

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 agent-free and agent-based task validation; Training, which updates the agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the agent's rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and Claw

Autonomous self-improvement could lead to uncontrolled growth.

ClawLoop enables AI agents to self-improve without external teacher models or human intervention, operating in sandbox environments with file system and shell access. This self-sustaining cycle, including task generation, training, and diagnosis, continuously enhances agent capabilities. While presenting efficiency, it raises significant concerns about autonomous AI development and control.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   6f4a81bb-6fc6-4259-8022-16c260c2db90
           https://arxiv.org/abs/2610.14118
   ↓
EVIDENCE   2 extracted excerpts
   ↓
MODEL RUN  3 runs, methodology 1.0.1
   ↓
SCORE      -17  (Mixed or uncertain)
   ↓
CONFIDENCE 60%