Metraipolis › archive › dc_58db00a3b3fb

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents — arXiv:2611.02075

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02075
License (as archived): CC0-1.0
Archived: 2026-11-03T11:02:33.073Z
SHA-256 of the archived text: 5c149661f8aa31c4dd61ac8f71d08229e632131bc5fcdde6afa4d07b642c74da
Stable URL of this page: https://metraipolis.com/documento/dc_58db00a3b3fb

How to cite

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents — arXiv:2611.02075 — arXiv (en), https://arxiv.org/abs/2611.02075 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58db00a3b3fb (Metraipolis archive dc_58db00a3b3fb, sha256 5c149661f8aa31c4dd61ac8f71d08229e632131bc5fcdde6afa4d07b642c74da)

BibTeX

@misc{dc58db00a3b3fb,
  title = {Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents — arXiv:2611.02075},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02075},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58db00a3b3fb; sha256 5c149661f8aa31c4dd61ac8f71d08229e632131bc5fcdde6afa4d07b642c74da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02075. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent decisions depend on empirical relationships that deployment observations reveal and task descriptions alone may leave unresolved. We introduce Decoupled Predictive Decision Making (DPDM), an architecture that formulates heterogeneous agent decisions as conditional prediction with a shared pretrained learner. Language models provide semantic representations of current and historical records, while a general-purpose conditional predictor predicts task-defined targets from the represented evidence. Pretraining supplies reusable inference capability; deployment evidence instantiates problem-specific predictions without updating either model's neural parameters. Tool judgments, candidate preferences, and reasoning assessments share an evidence-and-query interface, with predictions mapped to choices by a decision rule. This architecture establishes complementary sources of agent capability: semantic knowledge acquired through language pretraining and empirical inference acquired through structured-data pretraining. A single frozen LimiX-2 predictor serves all five task categories. With Qwen3.5-27B as the semantic encoder, DPDM raises mean accuracy across 50 benchmarks from 78.80% with few-shot prompting to 84.92% under their respective evaluated history budgets, and reaches 82.33% with identical histories and queries. On ToolPRMBench's BFCL and ToolSandbox tasks, absolute accuracy gains are 34.26% and 28.87%, respectively, at the methods' respective evaluated history budgets. Accuracy improves as history grows. With identical imbalanced histories, mean balanced accuracy improves by an absolute 14.51% across five reasoning-step assessment tasks and four encoders. DPDM makes learning from experience an independently improvable foundation-model capability, creating a shared route for advances in conditional prediction to improve decisions across agent tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02075 — 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 2026-11-03T10:59:45.803Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).