Newest papers

PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

Viral Patel, Boyin Tan, Jason Xue, Youcheng Sun · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29870 · open-access PDF

Korean

코딩 에이전트는 저장소 탐색 및 테스트에 상당한 노력을 투자할 수 있지만 여전히 실패한 패치를 생성합니다.현재의 온라인 조종 방법은 경로를 정기적으로 검토하거나 모니터가 행동 문제를 감지할 때 조언자를 호출합니다; 빈번한 리뷰는 비용이 많이 들며, 비정상적인 행동이 없다는 것은 에이전트가 올바른 경로에 있다는 것을 의미하지 않습니다.우리는 단일 계획 개입으로 코딩 에이전트를 조종하는 프레임 워크인 PAUSE를 제안합니다. 에이전트는 탐색, 버그 재생 및 테스트 후 경로 진행 중 60%의 중간에 최초의 소스 코드 편집에 도달합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Coding agents can invest substantial effort in repository exploration and testing yet still produce unsuccessful patches. Existing online steering methods review trajectories periodically or invoke an advisor when a monitor detects behavioral problems; frequent reviews are costly, and the absence of anomalous behavior does not mean that an agent is on the right track. We propose PAUSE, a framework for steering coding agents with a single planning intervention. Agents reach their first source-code edit at a median of 60% of trajectory progress, after exploration, bug reproduction, and testing.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29870, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange