ByteDance Paper: Keeping Messy History Outperforms Neat Summaries
rohanpaul_ai · x · 2026-08-31
A new ByteDance paper proposes Chain-of-Experience, suggesting that for test-time improvement, keeping the messy history of attempts works better than summarizing it into memory.
Key Findings:
- Across math, coding, and knowledge benchmarks, self-feedback achieved 71.0% accuracy, beating iterative solving without feedback (66.8%).
- With correctness or executor feedback, accuracy reached 79.3%.
- Overall improvement of 5.6% with 19% lower API costs.
- No weight changes are involved, making this contextual adaptation.
Takeaway: For agents, preserve the trajectory and add reliable feedback; compress only when safe.
More from coding & agent
- Dev shares a dirt-cheap approach to visual diffs — zeeg · 2026-09-01
- Grok Bot automates Shopify updates and supplier coordination — billyjhowell · 2026-09-01
- Investor calls GrokBot the next ChatGPT moment: 3 minutes beats hours of work — 新智元 · 2026-09-01
- Grok Bot automates lost deal analysis by mining call and email threads — lennysan · 2026-09-01
- Design pattern: immutable agent artifact revisions behind a stable review URL — RocketSeven · 2026-09-01
- Building a long-term memory benchmark for agents: what to add? — True_Mongoose_7073 · 2026-09-01