Metraipolis › archive › dc_3d34bb75fdcd

Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost — arXiv:2611.03852

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03852
License (as archived): CC0-1.0
Archived: 2026-11-04T18:35:44.796Z
SHA-256 of the archived text: 60b719b557589a592270ba158b73f68606065806923139fab59209acbffe5309
Stable URL of this page: https://metraipolis.com/documento/dc_3d34bb75fdcd

How to cite

Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost — arXiv:2611.03852 — arXiv (en), https://arxiv.org/abs/2611.03852 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d34bb75fdcd (Metraipolis archive dc_3d34bb75fdcd, sha256 60b719b557589a592270ba158b73f68606065806923139fab59209acbffe5309)

BibTeX

@misc{dc3d34bb75fdcd,
  title = {Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost — arXiv:2611.03852},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03852},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d34bb75fdcd; sha256 60b719b557589a592270ba158b73f68606065806923139fab59209acbffe5309},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03852. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reasoning substantially improves language models' ability to solve difficult problems, but long reasoning traces make these gains expensive. Efficient reasoning should express useful analysis in fewer tokens by reducing repetition and text that adds little value to solving the problem. Progress in proprietary models motivates this goal, yet their hidden scratchpads limit direct study of how it is achieved. We investigate whether open-weight models can generate less verbose reasoning by changing the form of their own earlier thoughts, without retraining. Our intervention rewrites prior reasoning into compact state records before pending tool results are revealed, then compares continuations from original and compact histories. Across the tested models, accepted compact histories usually shorten future reasoning; a coding case study also shows less repeated verification after a shared candidate solution. In software-agent deployments, compaction can reduce total spending, although task quality and rewrite-inclusive time depend on the target and compressor. These findings identify reasoning history as one way to reduce future reasoning-token use and motivate model-specific compaction policies evaluated for both efficiency and retained capability.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03852 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:32:37.394Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).