Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination

• URL: http://arxiv.org/abs/2607.08403v1
• Date: Thu, 09 Jul 2026 12:28:39 GMT
• Title: Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
• Abstract summary: We show that G-Frame, an adaptive multi-agent framework integrating Bayesian and team game principles, establishes an automated closed-loop for high-quality data synthesis and model training.<n>By forcing the internalization of domain constraints through structured reasoning, we synthesized a specialized corpus of 363,045 chains-of-thought and 199,589 question-answer pairs.<n>The resulting 7B model OmniChem achieves performance parity with GPT 4o mini on custom benchmarks and ChemBench while exhibiting a 79.46% reduction in hallucinations relative to its base architecture.
• Score: 17.86707751994118
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic patterns rather than reproduce axiomatic reasoning, causing frequent hallucinations. Here, we show that G-Frame, an adaptive multi-agent framework integrating Bayesian and team game principles, establishes an automated closed-loop for high-quality data synthesis and model training. By forcing the internalization of domain constraints through structured reasoning, we synthesized a specialized corpus of 363,045 chains-of-thought and 199,589 question-answer pairs. The resulting 7B model OmniChem achieves performance parity with GPT 4o mini on custom benchmarks and ChemBench while exhibiting a 79.46% reduction in hallucinations relative to its base architecture. We further demonstrate the advanced capabilities of OmniChem in molecular design and synthesis planning. This work establishes a scalable paradigm utilizing adaptive multi-agents to overcome inherent reasoning deficiencies, offering a feasible pathway for accelerating knowledge discovery in specialized scientific fields.

Related papers

• Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents [4.4997270313537845]
  Inverse design of metal-organic frameworks (MOFs) requires searching a vast space where property labels are expensive and most machine-learning models reveal little about why a structure succeeds.<n>We introduce LLM4MOF, a closed-loop framework in which language-model agents reason about chemistry, build candidate MOFs, and test them in simulation.
  arXiv  Detail & Related papers  (2026-06-28T15:30:13Z)
• MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents [57.28652712579434]
  We present MolLingo, a multi-agent system that emulates the reasoning process of a chemist to automate molecular design.<n>MolLingo addresses this by coordinating a Literature Agent, a Chemist Agent, and an Orchestrator through a shared memory module, with each agent equipped with domain-specific tools.<n>As a case study in early-stage therapeutic design, MolLingo grounds the Chemist Agent's reasoning in binding site geometry and residue-level protein context.
  arXiv  Detail & Related papers  (2026-05-27T02:11:23Z)
• ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding [56.94419746470799]
  Large Language Models (LLMs) have revolutionized scientific text processing, but exhibit a significant capability gap when interpreting chemical reaction diagrams.<n>We propose the Chemical Visual Activation (ChemVA) framework, which employs a Visual Anchor mechanism to ground functional groups.<n>We evaluate our approach on OCRD-Bench, a newly constructed dataset featuring dense visual-semantic contexts.
  arXiv  Detail & Related papers  (2026-05-17T01:12:50Z)
• OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning [51.33849811496781]
  Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous dynamics by Partial Differential Equations (PDEs)<n>We propose OMNIFLOW, a multimodal-symbolic architecture designed to ground frozen LLMs in fundamental physical laws without requiring domain-specific parameter updates.<n>We evaluate it on a benchmark spanning microscopic turbulence, theoretical Navier-Stokes, and macroscopic global weather forecasting.
  arXiv  Detail & Related papers  (2026-03-16T18:29:01Z)
• Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization [22.850204283344524]
  We propose DESRO, a framework for deciphering scientific reasoning from outcomes.<n>By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic.<n>We instantiate this framework in molecule optimization, a pivotal stage in drug discovery.
  arXiv  Detail & Related papers  (2026-03-13T06:25:27Z)
• Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis [51.83339196548892]
  ChemCraft is a novel framework that decouples chemical reasoning from knowledge storage.<n>ChemCraft achieves superior performance with minimal inference costs.<n>This work establishes a cost-effective and privacy-preserving paradigm for AI-aided chemistry.
  arXiv  Detail & Related papers  (2026-01-25T04:23:34Z)
• ChemNavigator: Agentic AI Discovery of Design Rules for Organic Photocatalysts [0.0]
  ChemNavigator is an agentic AI system that autonomously derives structure-property relationships.<n>ChemNavigator autonomously identified six statistically significant design rules governing frontier orbital energies.
  arXiv  Detail & Related papers  (2026-01-23T07:44:28Z)
• Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery [0.0]
  Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles.<n>We present a systematic approach combining a reasoning-centric model architecture with Low-Rank Adaptation fine-tuning.<n> Evaluation reveals substantial improvements: the fine-tuned system achieves 96.3% format adherence, 97.4% chemical validity, and 74.4% synthesis feasibility.
  arXiv  Detail & Related papers  (2025-07-09T23:05:23Z)
• MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning? [51.85759493254735]
  MindGYM is a structured and scalable framework for question synthesis.<n>It infuses high-level reasoning objectives to shape the model's synthesis behavior.<n>It composes more complex multi-hop questions based on QA seeds for deeper reasoning.
  arXiv  Detail & Related papers  (2025-03-12T16:03:03Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.