做智能体框架或Agent Harness的开发者，终于有了一个可量化的优化指标——EFC能让你用相同算力把成功率翻三倍，值得点开论文细读。
一项新研究提出了有效反馈计算（EFC）指标，用于衡量智能体实际可用的反馈量，替代传统的原始token和工具调用计数。实验表明，原始计数只能解释33%-42%的智能体失败原因，而EFC的解释力达到99%。在相同计算预算下，仅通过按有效反馈重新分配资源，就能将智能体成功率从0.27提升至0.90。该研究将智能体框架设计从猜测转变为可预测的科学。
// Scaling Laws for Agent Harnesses // If you build agent harnesses, this one is worth your time. ...
// Scaling Laws for Agent Harnesses // If you build agent harnesses, this one is worth your time. (bookmark it) Most harness tuning treats every token and tool call as if volume is all that counts. New research shows that most of it does not. The work introduces Effective Feedback Compute (EFC), a coordinate that counts only the feedback an agent can actually act on. Raw token and tool-call counts explain agent failure at R2 of 0.33 to 0.42. EFC pushes that to 0.99. Why does it matter? Once you budget by useful feedback instead of raw volume, reallocation alone lifts success from 0.27 to 0.90 at the same compute. This also turns harness design from guesswork into something you can predict. Paper: arxiv.org/abs/2605.29682 Learn to build effective AI agents in our academy: academy.dair.ai 💬 7 🔄 10 ❤️ 40 👀 3136 📊 22 ⚡