# GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning

arXiv: https://arxiv.org/abs/2505.23399 · HTML: https://mlsanity.com/paper/2505.23399/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 36 of its 76 references that are in the map.
- First posted on arXiv 29 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [A Survey of Vision-Language Pre-Trained Models](https://mlsanity.com/paper/2202.10936/) (2022)
- [Benchmarking LLMs via Uncertainty Quantification](https://mlsanity.com/paper/2401.12794/) (2024)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning](https://mlsanity.com/paper/2011.00597/) (2020)
- [Learning in Mean Field Games: A Survey](https://mlsanity.com/paper/2205.12944/) (2022)
- [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023)

## Built on by (most cited first, 30 of 58)

- [CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification](https://mlsanity.com/paper/2508.21046/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution](https://mlsanity.com/paper/2507.23348/) (2025)
- [LongCodeZip: Compress Long Context for Code Language Models](https://mlsanity.com/paper/2510.00446/) (2025)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off](https://mlsanity.com/paper/2509.02785/) (2025)
- [JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization](https://mlsanity.com/paper/2511.23002/) (2025)
- [OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration](https://mlsanity.com/paper/2509.04876/) (2025)
- [Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control](https://mlsanity.com/paper/2508.08134/) (2025)
- [FastVMT: Eliminating Redundancy in Video Motion Transfer](https://mlsanity.com/paper/2602.05551/) (2026)
- [Failure-Driven Workflow Refinement](https://mlsanity.com/paper/2510.10035/) (2025)
- [Top-Down Semantic Refinement for Image Captioning](https://mlsanity.com/paper/2510.22391/) (2025)
- [LastingBench: Defend Benchmarks Against Knowledge Leakage](https://mlsanity.com/paper/2506.21614/) (2025)
- [RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability](https://mlsanity.com/paper/2510.22710/) (2025)
- [Cost-Effective Communication: An Auction-based Method for Language Agent Interaction](https://mlsanity.com/paper/2511.13193/) (2025)
- [CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor](https://mlsanity.com/paper/2509.09703/) (2025)
- [3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale](https://mlsanity.com/paper/2511.13211/) (2025)
- [FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models](https://mlsanity.com/paper/2512.20561/) (2025)
- [Group Editing: Edit Multiple Images in One Go](https://mlsanity.com/paper/2603.22883/) (2026)
- [RLAE: Reinforcement Learning-Assisted Ensemble for LLMs](https://mlsanity.com/paper/2506.00439/) (2025)
- [STORM: Search-Guided Generative World Models for Robotic Manipulation](https://mlsanity.com/paper/2512.18477/) (2025)
- [CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation](https://mlsanity.com/paper/2512.22536/) (2025)
- [GlyphBanana: Advancing Precise Text Rendering Through Agentic Workflows](https://mlsanity.com/paper/2603.12155/) (2026)
- [HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution](https://mlsanity.com/paper/2509.00189/) (2025)
- [MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer](https://mlsanity.com/paper/2512.07500/) (2025)
- [Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents](https://mlsanity.com/paper/2512.08870/) (2025)
- [SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning](https://mlsanity.com/paper/2601.04699/) (2026)
- [ConSensus: Multi-Agent Collaboration for Multimodal Sensing](https://mlsanity.com/paper/2601.06453/) (2026)
- [GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction](https://mlsanity.com/paper/2508.20828/) (2025)

## Abstract (arXiv)

We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6%, and still enhances strong models like GPT-4o by up to 2--3%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.