Newest papers

Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources

Saiyue Lyu, Jerrold Huang, Yunbei Zhang, Janet Wang, Zhenting Wang, Yingqiang Ge, Haibo Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28834 · cited by 0 works (OpenAlex) · open-access PDF

Korean

인퍼런스 타임 스케일링은 종종 토큰 예산 문제로 취급되지만, 실패한 코딩 에이전트는 계산, 정보 또는 피드백과 같은 질적으로 다른 리소스를 찾을 수 있습니다. Banzhaf Resource Attribution (BRA)는 각 리소스의 수리 및 상호 작용에 대한 제한적 기여를 측정하는 제어된 요소 프레임 워크이며, 실패한 상태 및 개정 프로토콜을 고정하면서 실패한 상태를 유지합니다. 우리는 MBPP+ 및 HumanEval+의 194개의 기능 수준의 실패와 SWE-bench Verified의 126개의 저장소 수준의 실패에 대한 6개의 모델을 평가합니다. 작업 관련 사양은 수리를 지속적으로 향상시킨 반면, 공공 테스트 피드백은 소규모 이득을 제공

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

Abstract

Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We introduce Banzhaf Resource Attribution (BRA), a controlled factorial framework that measures each resource's marginal contribution to repair and its interactions while holding the failed state and revision protocol fixed. We evaluate six models on 194 function-level failures from MBPP+ and HumanEval+ and 126 repository-level failures from SWE-bench Verified. Task-relevant specifications consistently improve repair, whereas public-test feedback provides small gains and retrieved code little to none. The value of additional computation declines with model capability, while information remains useful; resource channels largely exhibit diminishing returns, although complementary information can reinforce itself. Yet three of four frontier models select feedback in 95-100% of cases and obtain lower gains than uniform random resource selection. BRA thus exposes a gap between the resources agents prefer and those that measurably improve repair.

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

Topics: Attribution, Computer science, Coding (social sciences), Resource (disambiguation), Protocol (science), Marginal value

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