ByteDance Paper: Keeping Full History Cuts Costs by 19% vs. Compression

AGI Hunt · wechat · 2026-08-31

ByteDance's Chain-of-Experience paper investigates how AI agents should handle past attempts during iterative solving. Contrary to intuition that compression saves context, experiments show retaining the full history with feedback signals achieves a 71.0% average accuracy across 8 models and 6 benchmarks, outperforming non-iterative solving (66.8%). Despite longer context windows, faster convergence reduces total API costs by 19%. The study suggests that feedback on "why it went wrong" holds more value than compressed result summaries, validating a "less is more" context strategy.

Related event: ByteDance Paper: Keeping Full Trial History Beats Summarized Memory for LLM Agents(3 posts)→

Original post →

More from coding & agent

coding & agent channel →