---
title: "摊销贝叶斯实验设计：面向LLM的序贯信息收集方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.03426v1"
permalink: "https://feed.astralor.com/items/itm_dd3a5f549632850972bd5726"
published: "2026-07-03T15:38:17.000Z"
score: 78
channel: "ai"
tags: ["ASIG","GRPO","LLM","序贯信息收集","贝叶斯实验设计"]
---

# 摊销贝叶斯实验设计：面向LLM的序贯信息收集方法

## AI 点评

> 这篇论文最吸引我的是将贝叶斯实验设计“摊销”进LLM策略，而非在推理时执行昂贵的BED优化，在提升成功率的同时大幅降低计算开销。对于从事对话系统、智能问答或任何需要多轮信息获取的开发者来说，这一思路极具启发性——它暗示了可以通过微调让模型自己学会问“好问题”，而不是依赖外部搜索或规则。此外，在医疗诊断任务上的迁移能力证明了方法的通用性，值得关注。

## 速览

大型语言模型在多轮交互中常难以高效收集信息。本文提出ASIG方法，通过多轮扩展的GRPO和期望信息增益奖励，将贝叶斯实验设计摊销到LLM策略中。在20 Questions任务上，ASIG使7B基座模型成功率翻倍，推理成本降低25倍以上；在MediQ医疗诊断任务上，其信息收集策略展现出跨任务迁移能力。该方法为序贯决策中的高效信息收集提供了新范式。

## 关键点

- 提出ASIG方法，将贝叶斯实验设计通过多轮GRPO摊销到LLM策略中。
- 在20 Questions任务中，7B模型成功率翻倍，推理成本降低25倍以上。
- 在未见的MediQ医疗诊断基准上表现出策略迁移能力。

## 全文

Large language models (LLMs) exhibit strong reasoning and world-knowledge capabilities, yet often struggle to gather information effectively across the multi-turn interactions required in sequential decision-making settings. We introduce Amortised Sequential Information Gathering (ASIG), a fine-tuning approach that amortises Bayesian Experimental Design (BED) into LLM policies via a multi-turn extension of Group Relative Policy Optimisation with an Expected Information Gain reward. Evaluated on the 20 Questions task, ASIG more than doubles the success rate of the 7B base model and reduces inference cost by over $25\times$ relative to BED-LLM, a competitive inference-time baseline. Applied to MediQ, a medical diagnosis benchmark unseen during training, ASIG improves information-seeking performance at the 7B scale, suggesting that the learned strategies can transfer out of distribution. Our findings show that amortising BED into LLM policies provides an effective and computationally efficient approach to sequential information gathering.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_dd3a5f549632850972bd5726