arXiv cs.MA· Fabrizio Marozzo, Pietro Li\`o·· 2 天前AI 评分22
LLM-as-an-Investigator：面向稳健交互式问题诊断的证据优先智能体推理方法
LLM-as-an-Investigator: Evidence-First Agentic Reasoning for Robust Interactive Problem Diagnosis
AI 导读
研究者提出 LLM-as-an-Investigator 证据优先方法，并实现 Solution Investigator Agent（SIA），通过共享调查状态协调 Diagnostic Reasoner、Hypothesis Investigator 和 Counterfactual Investigator 三种推理行为，减少过早锁定错误假设。
正文 · 原文
Abstract:Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain the same symptoms. Effective diagnosis requires acquiring discriminative evidence and selecting the explanation best supported by it. Yet reasoning or interaction alone may not prevent premature commitment to an incorrect hypothesis. We introduce LLM-as-an-Investigator, an evidence-first methodology for interactive problem diagnosis that reduces premature commitment while distinguishing competing causes. We implement it through the Solution Investigator Agent (SIA), which orchestrates three complementary reasoning behaviours through a shared investigation state: a Diagnostic Reasoner that conducts and reassesses the diagnostic interview, a Hypothesis Investigator that maintains and updates competing hypotheses, and a Counterfactual Investigator that challenges current explanations and guides discriminative follow-up questions. Final selection uses cited dialogue evidence and a separate verification step, while explicit hypothesis and evidence records make the diagnosis traceable and preserve unresolved alternatives. We construct a structured corpus from 303 technical forum threads across mechanical, electrical, and hydraulic domains. A source-grounded pipeline separates the initial problem, pre-solution clarifications, and reported outcome, while a user simulator answers diagnostic questions without access to the reference solution. We compare SIA with direct, reasoning-based, interactive, and search-based baselines, including adaptations of ReAct and Tree of Thoughts. Evaluation distinguishes final diagnostic quality from hypothesis coverage and oracle potential, while ablations and paired stress tests assess component contributions and robustness to plausible but misleading user hypotheses.
| Subjects: | Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2606.13220 [cs.AI] |
| (or arXiv:2606.13220v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.13220 arXiv-issued DOI via DataCite |
Submission history
From: Fabrizio Marozzo [view email]
[v1]
Thu, 11 Jun 2026 11:37:07 UTC (120 KB)
[v2]
Tue, 13 Oct 2026 22:22:05 UTC (149 KB)
来源：arXiv cs.MA · arxiv.org