解耦式預測決策:面向智能體的共享條件預測器
Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents
DPDM 結合凍結的語言模型表示與共享的預訓練條件預測器,讓智能體從部署證據中作出預測,而無須更新模型參數。採用 Qwen3.5-27B 作語義編碼器時,DPDM 在 50 項基準測試的平均準確率為 84.92%,高於少樣本提示的 78.80%;使用相同歷史資料和查詢時,準確率為 82.33%。單一凍結的 LimiX-2 預測器涵蓋五類任務,準確率亦隨歷史資料增加而提升。
Published on Nov 1
Authors:
,
,
,
,
,
Abstract
DPDM improves agent decision accuracy by combining frozen language-model representations with a shared pretrained conditional predictor that learns from deployment evidence without parameter updates.
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.
View arXiv page View PDF Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.02075 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.02075 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.02075 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co