arXiv cs.AI· Kaiwen Shi, Zheyuan Zhang, Weixiang Sun, Han Bao, Colby Nelson, Yanfang Ye·· 10 小时前AI 评分31
LProp:让 LLM 智能体通过证据条件信念修正传播潜在不确定性
LProp: Propagating Latent Uncertainty through Evidence-Conditioned Belief Revision in LLM Agents
AI 导读
研究者提出潜在空间估计器 Latent Uncertainty 及基于它的 LProp(潜在不确定性传播),利用潜在表示与新证据修正继承的答案分布,无需额外轨迹采样。在多项选择、是非、开放式问答和数学推理任务上,该方法多数指标优于基线,LProp 在全部八种传播设置中平均推理 token 用量最低。特征消融显示,继承的潜在内容比答案概率或单纯模型容量更能改善错误恢复。
正文 · 原文
Abstract:When LLM agents pass intermediate judgments downstream without uncertainty, later decisions may treat tentative assumptions as facts. Effective uncertainty propagation must preserve information for correction and update inherited beliefs as new evidence arrives. Yet scalar scores omit information needed for revision, while detailed descriptions and reflection incur additional costs. We introduce Latent Uncertainty, a latent-space estimator that preserves uncertainty-relevant information without lengthy descriptions. Building on this, we propose LProp (Latent Uncertainty Propagation), which revises inherited answer distributions using latent representations and new evidence without additional trajectory sampling. We evaluate both methods across multiple-choice, yes/no, open-ended question answering, and mathematical reasoning tasks. Our approach outperforms baselines on most metrics, while LProp achieves the lowest mean inference-token usage in all eight propagation settings. Matched feature ablations further demonstrate that inherited latent content improves error recovery beyond answer probabilities or model capacity alone.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23564 [cs.AI] |
| (or arXiv:2611.23564v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23564 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kaiwen Shi [view email]
[v1]
Tue, 17 Nov 2026 22:12:54 UTC (1,111 KB)
来源:arXiv cs.AI · arxiv.org