HarnessMM：通过守护式决策复用降低 Agent token 消耗
HarnessMM: Recursive Self-Improvement for Harness Token Efficiency
一篇关于省 token 的论文：HarnessMM 把 Agent 已经决定过的动作存起来直接复用，DeepSeek harness 的 token 用量直接降到原来的 12%。
论文提出 HarnessMM，在模型与工具边界设置控制器，复用已解析的决策来替代后续的推理回调，actor 权重保持不变。递归自改进（RSI）根据训练反馈迭代优化 harness 配置，由验证环节选出部署版本。在 HumanEval 上，Codex 成功率保持 90.82%，每任务 token 从 66.72k 降至 47.02k，节省 29.54%。在 DeepSeek Harness 上，成功率从 71.43% 升至 85.71%，每任务 token 从 96.28k 降至 11.62k，节省 87.93%。MBPP 消融实验显示，其成本比单次使用图低 26.91%，比保留回调低 19.52%。
HarnessMM: Recursive Self-Improvement for Harness Token Efficiency
Agent harnesses repeatedly invoke reasoning after tool feedback, even when an earlier call has already fixed the next action. We introduce HarnessMM (Harness Minus Minus), a method for improving harness token efficiency through guarded decision reuse and recursive self-improvement (RSI). RSI iteratively refines companion harness configurations from training feedback, with validation selecting the configuration for deployment. A controller at the model-tool boundary reuses resolved decisions to replace later reasoning callbacks while actor weights remain fixed. Executable Decision Graphs store exact actions, literal arguments, causal dependencies, and public guards. Guarded Decision Reuse activates these persistent decisions from observed receipts; Certified Callback Substitution executes them through the native interface and records removal of the registered slow callback. New semantic decisions, unsupported evidence, and selector abstention invoke the original actor again. The representation restricts what feedback may change, while complete-task measurements establish quality and cost. On HumanEval, HarnessMM preserves Codex success at 90.82\% while reducing Tokens/task (k) from 66.72 to 47.02 (29.54\% saving). For DeepSeek Harness, success rises from 71.43\% to 85.71\% while Tokens/task (k) fall from 96.28 to 11.62 (87.93\% saving). A separate MBPP ablation measures 26.91\% lower cost than single-use graphs and 19.52\% lower cost than retained callbacks. These results establish guarded decision reuse as a practical way to reduce repeated reasoning in existing harnesses.