Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 17 of its 35 references that are in the map. First posted on arXiv 9 Jul 2026.
Builds on
17 of 35 references.
References · 17
- 2017Attention Is All You Needcited by 59,932
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
- 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
- 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
- 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 531
- 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
- 2023How Language Model Hallucinations Can Snowballcited by 310
- 2023Role-Play with Large Language Modelscited by 290
5 more
- 2024ChemLLM: A Chemical Large Language Modelcited by 100
- 2024Towards Building Multilingual Language Model for Medicinecited by 91
- 2022Inverse scaling can become U-shapedcited by 76
- 2024A quantitative analysis of knowledge-learning preferences in large language models in molecular sciencecited by 18
- 2024Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Languagecited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
- 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
- 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
- 2026Clueing up LLMs with Tool-Augmented Deductive Reasoning
- 2025OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
- 2026FALSIFYBENCH: Evaluating Inductive Reasoning in LLMs with Rule Discovery Games
- 2024Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models
- 2025Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning