Paper: rewriting reasoning histories into compact records cuts agent token costs
Anton Hristov · hf · 2026-11-05
Anton Hristov's paper studies the causal effects of reasoning-history compaction: without retraining, rewriting long reasoning traces into compact state records substantially reduces future reasoning length and token costs in open-weight models. Inspired by hints that GPT-5.5 uses a compact scratchpad, the author runs causal experiments on open models, showing that compressing history instead of carrying it verbatim is a practical lever for agent cost optimization.
More from coding & agent
- Linear CEO Karri Saarinen on quality-obsessed design and whether the playbook survives the agentic era — soleio · 2026-11-05
- Hiring an AI employee for ghostwriting's "second job": voice guides, calendars, and approval queues — nikola_mr64990 · 2026-11-05
- Gabriel Chua builds talk slides with ChatGPT Sites and his personal agent dot — gabrielchua · 2026-11-05
- Dots vs Codex: let your personal agent supervise your Codex threads — gabrielchua · 2026-11-05
- Cohere paper: agents find injected solutions in 80% of runs but exploit them only 37-50% of the time — burny_tech · 2026-11-05
- Tencent Hunyuan builds a demolition game from scratch and self-fixes a physics bug from its own screenshot — prasenx · 2026-11-05