Tiny Moves: Game-based Hypothesis Refinement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dobrowolska, Agnieszka, Hintzen, Rogier, Balla, Martin, Gemayel, Karl, Reichert, Sabine, Charman, Thomas, Lim, Jen Ning, Edwards, Lindsay, Gogleva, Anna
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910017825800192
author Dobrowolska, Agnieszka
Hintzen, Rogier
Balla, Martin
Gemayel, Karl
Reichert, Sabine
Charman, Thomas
Lim, Jen Ning
Edwards, Lindsay
Gogleva, Anna
author_facet Dobrowolska, Agnieszka
Hintzen, Rogier
Balla, Martin
Gemayel, Karl
Reichert, Sabine
Charman, Thomas
Lim, Jen Ning
Edwards, Lindsay
Gogleva, Anna
contents Most machine learning approaches to scientific discovery frame hypotheses as end-to-end predictions, obscuring the incremental structure of scientific reasoning. We propose The Hypothesis Game, a symbolic formalism for hypothesis refinement in which LLM agents operate on a shared hypothesis state using a fixed grammar of reasoning moves. The framework is motivated by the observation that scientific progress often proceeds through small, localized revisions, grounded in domain context, rather than extensive rewrites. We instantiate a minimal game with LLM agents and evaluate it on pathway-level mechanistic refinement tasks. In the primary setting of corruption recovery, where hypotheses contain controlled errors, the game-based approach consistently removes more errors and achieves higher precision than strong prompting baselines, while preserving valid structure through incremental edits. In a secondary reconstruction setting from partial cues, it performs comparably to the strongest baseline, indicating that explicit move-based refinement remains competitive even when ground-truth recovery is difficult. These findings support game-based reasoning as a principled route to more controllable, interpretable, and transferable hypothesis refinement systems for scientific discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2602_09801
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tiny Moves: Game-based Hypothesis Refinement
Dobrowolska, Agnieszka
Hintzen, Rogier
Balla, Martin
Gemayel, Karl
Reichert, Sabine
Charman, Thomas
Lim, Jen Ning
Edwards, Lindsay
Gogleva, Anna
Multiagent Systems
Most machine learning approaches to scientific discovery frame hypotheses as end-to-end predictions, obscuring the incremental structure of scientific reasoning. We propose The Hypothesis Game, a symbolic formalism for hypothesis refinement in which LLM agents operate on a shared hypothesis state using a fixed grammar of reasoning moves. The framework is motivated by the observation that scientific progress often proceeds through small, localized revisions, grounded in domain context, rather than extensive rewrites. We instantiate a minimal game with LLM agents and evaluate it on pathway-level mechanistic refinement tasks. In the primary setting of corruption recovery, where hypotheses contain controlled errors, the game-based approach consistently removes more errors and achieves higher precision than strong prompting baselines, while preserving valid structure through incremental edits. In a secondary reconstruction setting from partial cues, it performs comparably to the strongest baseline, indicating that explicit move-based refinement remains competitive even when ground-truth recovery is difficult. These findings support game-based reasoning as a principled route to more controllable, interpretable, and transferable hypothesis refinement systems for scientific discovery.
title Tiny Moves: Game-based Hypothesis Refinement
topic Multiagent Systems
url https://arxiv.org/abs/2602.09801