Metraipolis › archive › dc_7ea1df87be6e

How Much Conversation History Does an AI Agent Need? — arXiv:2611.09662

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.09662
License (as archived): CC0-1.0
Archived: 2026-11-09T22:35:11.123Z
SHA-256 of the archived text: fb9da50c531cafc5eff0b941a31fbcbcafa52bc091753116a9976370fb518fd5
Stable URL of this page: https://metraipolis.com/documento/dc_7ea1df87be6e

How to cite

How Much Conversation History Does an AI Agent Need? — arXiv:2611.09662 — arXiv (en), https://arxiv.org/abs/2611.09662 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ea1df87be6e (Metraipolis archive dc_7ea1df87be6e, sha256 fb9da50c531cafc5eff0b941a31fbcbcafa52bc091753116a9976370fb518fd5)

BibTeX

@misc{dc7ea1df87be6e,
  title = {How Much Conversation History Does an AI Agent Need? — arXiv:2611.09662},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09662},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ea1df87be6e; sha256 fb9da50c531cafc5eff0b941a31fbcbcafa52bc091753116a9976370fb518fd5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09662. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How does using less conversational history change reader-token use and benchmark scores? We examine this question on 1,100 BEAM questions. We held the retrieval ranking and reader constant across five fixed passage budgets, and mean assigned scores rose as the passage budget grew. The score gain per additional token became smaller at the upper tested budgets. Answerable questions generally received higher scores with more context. Pooled abstention scores sometimes rose as the passage budget shrank. We also tested message retention in a controlled task with explicit conversational-state targets and compared retained user messages with token-matched recency. Qwen matched the full state more often for direct requirements when user messages were retained. Its full-state matching declined when answers depended on references to earlier offers. Mistral produced near-floor results across the retention conditions. A scoring audit leaves the correctness of BEAM answers unresolved. These experiments characterize the token and score consequences of the tested memory budgets. Reliable budget selection depends on retaining the evidence each question requires and validating the measure used to assess answer quality.

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/2611.09662 — 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 2026-11-09T22:30:47.338Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).