通过运行时系统优化，让模型在复杂任务中准确率突破95%。
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
- 构建状态驱动的执行系统，实现可回溯、可检查的流程控制。
- 在终端基准上达95.3%准确率，仅需15美元推理成本。
- 适用于多模型迁移，尤其适合需要稳定执行的自动化场景。
长周期智能体即使底层模型能完成单步任务，仍可能因状态丢失、记忆失效或流程跳过而失败。本文提出StateM，一种不修改模型权重的原生运行时系统，通过持久化状态、局部上下文、校验转移、可恢复的执行手册和版本化操作规范，提升执行可靠性。在Terminal-Bench 2.1上，StateM使GPT-5.6 Sol xhigh达到95.3%原始准确率（445次试验），所有89个任务至少成功一次；冻结配置下，GPT-5.6 Luna从76.7%提升至85.4%，超过84.9%的Sol xhigh基准。相同系统使DeepSeek-V4 Flash在标准超时下从82.7%提升至88.1%，核心任务集达89.1%；仅扩展延迟敏感任务即匹配88.8%的GPT-5.6 Sol峰值结果。最终评分API成本约15美元（原参考为574.68美元），总支出52.22美元。BusinessBench上，基于开发集构建的专用手册在保留数据上分别提升0.55宏观与1.34微观得分，机制匹配家族提升10.04点。具体规则在结构相似任务中可泛化，控制方法具广泛适用性。
原文摘要 · Abstract (English)
Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate lessons from earlier executions, skip known procedures, or stop prematurely. We bet on harness scaling to improve the execution system around an agent without changing its model weights. We introduce StateM, an agent-native runtime that organizes execution around durable states, phase-local context, checked transitions, recoverable runbooks, and versioned procedural practices that agents and users can inspect together. On Terminal-Bench 2.1, StateM raises GPT-5.5 xhigh to 92.1\%, versus 83.1\% reference and GPT-5.6 Sol Ultra at 91.9\%. The runbook transfers unchanged to GPT-5.6. With GPT-5.6 Sol xhigh, StateM reaches 95.3\% raw accuracy across 445 trials and succeeds on all 89 tasks at least once. The frozen profile raises GPT-5.6 Luna from 76.7 to 85.4\%, above the 84.9\% Sol xhigh reference. Using the same runtime, runbook structure, and golden rules, less than \$38 of adaptation raises DeepSeek-V4 Flash from 82.7 to 88.1\% under standard timeouts and to 89.1\% on an 88-task common core. Extending only the remaining latency-sensitive task matches the reported 88.8\% GPT-5.6 Sol max result. Final-score API usage is about \$15 versus \$574.68 for the GPT reference; total DeepSeek expenditure is \$52.22. On BusinessBench, family-specific runbooks built on development sets yield held-out gains of 0.55 macro and 1.34 micro points; two mechanism-matched families improve by 10.04 points. Concrete rules generalize when tasks share execution structure, while the control methodology applies broadly. StateM turns selected postmortem findings into persistent, executable preconditions and practices, making learned controls explicit and enforceable through stateful controls. Code at github.com/henryqin1997/statem.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。