Harness², 재귀적 자기 개선으로 에이전트 적응력 향상
Harness^2: Recursive Agent Harnessing for an Open World
- 매체
- arXiv
- 게시
- 중요도
- 3/5
- 화제 지수
- 3
한국어 요약
Harness²는 검증자 없이 에이전트 실행 환경을 온라인으로 개선하는 재귀적 에이전트 하네스 프레임워크다. 작업 수준 재귀와 하네싱 수준 재귀 두 계층을 통해 작업별 최적화를 일반화 가능한 경험으로 변환하며, WorkBuddy-Bench에서 최대 11.5점, JobBench에서 4.5점, LAB에서 11.8 포인트 성능 향상을 기록했다.
원문 발췌 · English
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses. However, deploying RSI in open-world settings still faces two critical challenges. First, open-world tasks are typically unseen during the harness design phase and novel at test time, leaving no ground-truth verifiers to reliably guide online harness edits. Second, the RSI process remains highly task-specific and fails to generalize to novel scenarios. We introduce Harness^2, a plug-and-play, recursive agent harnessing framework that addresses these challenges through two connected levels of recursion. Task-level recursion refines the current task's harness using a contrastive Propose-Probe-Compose step that reliably guides edits without ground-truth verifiers, and can be scaled further via parallel or sequential recursion. Harnessing-level recursion then extracts experience from these edits to update a continual improvement harness, enabling the agent to better adapt to future tasks. Across three professional benchmarks and four model-harness configurations, a single step consistently improves GLM-5 and Gemini 3.5 Flash over their base harnesses, yielding gains of up to 11.5 points on WorkBuddy-Bench, 4.5 points on JobBench, and 11.8 percentage points on LAB, with further gains as the task-level recursion budget increases.