# SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models

arXiv: https://arxiv.org/abs/2608.17501 · HTML: https://mlsanity.com/paper/2608.17501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 13 of 13)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents](https://mlsanity.com/paper/2503.24047/) (2025)
- [A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery](https://mlsanity.com/paper/2406.10833/) (2024)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Regret Minimization in Heavy-Tailed Bandits](https://mlsanity.com/paper/2102.03734/) (2021)
- [HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance](https://mlsanity.com/paper/2506.12937/) (2025)
- [On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists](https://mlsanity.com/paper/2605.20668/) (2026)
- [Diffusion Models Meet Contextual Bandits](https://mlsanity.com/paper/2402.10028/) (2024)
- [MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier](https://mlsanity.com/paper/2603.03756/) (2026)
- [Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts](https://mlsanity.com/paper/2606.09105/) (2026)

## Abstract (arXiv)

Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft scientific manuscripts. However, during the early stages of research, when research problems are formulated, these AI scientists often rely heavily on proprietary frontier models. Their proposals are shaped by opaque parametric knowledge and by literature searches conditioned on the proposals themselves. Such knowledge is effectively a black box, and this dependence makes the evidential basis and validity of generated research problems difficult to audit and leaves the process vulnerable to model-specific hallucinations and biases. Furthermore, if proprietary research materials are transmitted to external APIs, the use of these models creates confidentiality, privacy, and data-governance concerns. We introduce the Structural Gap Hypothesis Agent (SGHA), a fully automated, corpus-first research-problem discovery system that runs entirely on a local LLM. SGHA structures a scientific literature corpus into evidence-linked paper objects and a typed evidence graph, detects unresolved structural patterns across papers, screens candidate gaps before formulation, and produces traceable research-problem families. In particular, it is able to output assumptions, objectives, success criteria, and remaining ambiguities. All LLM-based components of SGHA are executed using a locally served open-weight 9B language model, without requiring proprietary frontier-model APIs. We compare SGHA with the AI Scientist-v2 idea formulation module in five machine-learning domains. Our results suggest that explicit corpus structure and evidence-constrained reasoning can support promising, inspectable research-problem formulation without relying on frontier models during generation or verification.