# 字节跳动新论文：保留尝试历史比整理成记忆摘要更有效

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-31 22:02
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmthbps8c09eerodmvd0uc8oa
- 原文链接：https://x.com/rohanpaul_ai/status/2094425720005234923

## AI 摘要

字节跳动新论文提出 Chain-of-Experience 方法，在上下文中保留先前尝试与反馈而非整理成简洁摘要。在 6 个数学、编程和知识基准上，自我反馈平均得分 71.0%，高于无反馈迭代求解的 66.8%；使用正确性或执行器反馈可达 79.3%。

## 正文

New ByteDance paper shows for test-time improvement, keeping the messy history of attempts can work better than turning that history into a neat memory summary.

Chain-of-Experience keeps earlier attempts and feedback in context, then asks the model to try again. Across 6 math, coding, and knowledge benchmarks, self-feedback averaged 71.0%, versus 66.8% with iterative solving but no feedback; correctness or executor feedback reached 79.3%.

The paper also reports 5.6% overall improvement with 19% lower API cost across tasks and models when feedback is used.

No weights change here, so this is contextual adaptation rather than persistent learning. Self-feedback also hurt on BrowseComp-Plus when solving the task required external search.

For agents, preserve the trajectory, add reliable feedback, and compress only when you know what can safely disappear.