为代理编程扩展测试时计算
Scaling Test-Time Compute for Agentic Coding
AI总结：
本文提出基于轨迹紧凑表示的代理编程测试时扩展框架，通过递归竞赛投票和并行-蒸馏-细化方法提升长周期代理性能，实验证明在SWE-Bench和Terminal-Bench上显著提升效果。
摘要：
测试时扩展已成为提升大语言模型的强大方法。然而，现有方法最适合于短且有界输出，可直接比较、排名或细化。长周期编程代理违反这一前提：每次尝试产生扩展的动作轨迹、观察、错误和部分进展。在此设置中，主要挑战不再是生成更多尝试，而是将先前经验表示为可有效选择和重用的形式。我们提出基于轨迹紧凑表示的代理编程测试时扩展框架。该框架将每个轨迹转换为结构化摘要，保留其关键假设、进展和失败模式，同时丢弃低信号轨迹细节。这种表示使两种互补的推理时扩展形式成为可能。对于并行扩展，我们引入递归竞赛投票（RTV），通过小群体比较递归缩小轨迹摘要群体。对于序列扩展，我们通过将新轨迹条件于先前尝试蒸馏出的摘要，将并行-蒸馏-细化（PDR）适应到代理设置。我们的方法在SWE-Bench Verified和Terminal-Bench v2.0上持续提升前沿代理性能。例如，使用我们的方法，Claude-4.5-Opus在SWE-Bench Verified（mini-SWE-agent）上从70.9%提升至77.6%，在Terminal-Bench v2.0（Terminus 1）上从46.9%提升至59.1%。我们的结果表明，长周期代理的测试时扩展本质上是表示、选择和重用的问题。
英文摘要：
Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that can be directly compared, ranked or refined. Long-horizon coding agents violate this premise: each attempt produces an extended trajectory of actions, observations, errors, and partial progress taken by the agent. In this setting, the main challenge is no longer generating more attempts, but representing prior experience in a form that can be effectively selected from and reused. We propose a test-time scaling framework for agentic coding based on compact representations of rollout trajectories. Our framework converts each rollout into a structured summary that preserves its salient hypotheses, progress, and failure modes while discarding low-signal trace details. This representation enables two complementary forms of inference-time scaling. For parallel scaling, we introduce Recursive Tournament Voting (RTV), which recursively narrows a population of rollout summaries through small-group comparisons. For sequential scaling, we adapt Parallel-Distill-Refine (PDR) to the agentic setting by conditioning new rollouts on summaries distilled from prior attempts. Our method consistently improves the performance of frontier coding agents across SWE-Bench Verified and Terminal-Bench v2.0. For example, by using our method Claude-4.5-Opus improves from 70.9% to 77.6% on SWE-Bench Verified (mini-SWE-agent) and 46.9% to 59.1% on Terminal-Bench v2.0 (Terminus 1). Our results suggest that test-time scaling for long-horizon agents is fundamentally a problem of representation, selection, and reuse.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
