cs.AINov 1, 2026

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

Authors: Lang Mo, Xingxuan Zhang, Qi Wang, Mingchao Hao, Hao Yuan, Chunjing Gan, Wang Lu, Peng Cui

Organizations: Stable AI · Tsinghua University

Abstract

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.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Dyad: Extending Large Language Models with Native Typed Decision-Making

    Sep 28, 2026Yundaichuan Zhan, Weishi Wang, Wenbiao Liu +5Language Model-Based ControlRL for LLM Agents

  2. MMDM: Measuring Massive Multitask Decision Making

    Nov 10, 2026Junhao Shen, Qing Zong, Yue Guo +3LLM Decision-MakingSystem One Decision Models

  3. JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

    Oct 15, 2026Kunlun Zhu, Tao Feng, Xu Han +5LLM Agent HarnessesLLM Agents