mlsanityData to 14 Oct 2026

Large Decision Models: Repurposing Large Language Models as Single-Pass Decision Makers

arXiv 2610.15501 ↗First posted 11 Oct 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models make decisions through parallel prefill and sequential decoding. Although effective, this approach incurs decoding costs and does not explicitly expose decision probabilities. Existing task-specific classifiers require per-task training and offer limited generalization to unseen decision schemas. We propose Large Decision Models (LDMs), repurposing language models to return explicit probabilities over labels specified at run time using one prefill forward pass. We first adapt models to this interface through Diverse Decision Supervision (DDS), covering varied domains, rules and labels. To further narrow the performance gap to a reasoning model, Self-Posed Reasoning Distillation (SPRD) adds tasks generated by a frozen teacher, filters them for answer consistency, and trains on label distributions obtained from repeated teacher reasoning. We evaluate on DecisionVista, pairing new-schema tests with held-out human-labelled sources. Across three base models, the recipe improves accuracy over a step-matched baseline by 1.8 and 1.5 percentage points, respectively, achieving a 182-fold speedup in latency over reasoning rollout on Gemma-4-31B. Reasoning remains stronger on the new-schema test, motivating a confidence router for uncertain decisions. On development sets, routing recovers a median 92% of reasoning's accuracy advantage while generating 27-58% of its tokens. Code is available at https://github.com/JianhuiWei7/LDM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

26 of 57 references.

References · 26

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  7. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  8. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  10. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 939
  11. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  12. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
14 more
  1. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  2. 2017Selective Classification for Deep Neural Networkscited by 852
  3. 2021Robust fine-tuning of zero-shot modelscited by 797
  4. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  5. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  7. 2022Large Language Models Can Self-Improvecited by 664
  8. 2026Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Modelscited by 455
  9. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
  10. 2022Large Language Models Are Reasoning Teacherscited by 329
  11. 2022Teaching Small Language Models to Reasoncited by 284
  12. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 235
  13. 2023Implicit Chain of Thought Reasoning via Knowledge Distillationcited by 176
  14. 2024Distilling System 2 into System 1cited by 159

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Diagnosing and Improving Probabilistic Reasoning in Large Language Models
  2. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  3. 2026Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
  4. 2025Training Language Models to Reason Efficiently
  5. 2024DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
  6. 2024Large Language Models Can Self-Improve in Long-context Reasoning
  7. 2025Efficient Inference for Large Reasoning Models: A Survey
  8. 2024Efficient Sequential Decision Making with Large Language Models