Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
This work addresses the problem of inefficient tool usage in retrieval-augmented LLMs for fact-seeking tasks, offering an incremental improvement in reliability.
The paper tackles the unreliability of large language models in fact-seeking question answering by proposing a modular framework that separates planning from retrieval and synthesis, improving accuracy and latency on the SEAL-0 benchmark.
Fact-seeking question answering with large language models (LLMs) remains unreliable when answers depend on up-to-date or conflicting information. Although retrieval-augmented and tool-using LLMs reduce hallucinations, they often rely on implicit planning, leading to inefficient tool usage. We propose a modular framework that explicitly separates planning from factual retrieval and answer synthesis. A lightweight student planner is trained via a teacher-student framework to generate structured decompositions consisting of abstract reasoning steps and searchable fact requests. The supervision signals contain only planning traces and fact requests, without providing factual answers or retrieved evidence. At inference, the planner produces plans, while prompt-engineered modules perform retrieval and response synthesis. We evaluate the proposed framework on SEAL-0, an extremely challenging benchmark for search-augmented LLMs. Results show that supervised planning improves both accuracy and latency compared to monolithic reasoning models and prompt-based tool-augmented frameworks, demonstrating that explicitly learned planning structures are essential for reliable fact-seeking LLMs.