MOSAIC: A Unified Platform for Cross-Paradigm Comparison and Evaluation of Homogeneous and Heterogeneous Multi-Agent RL, LLM, VLM, and Human Decision-Makers

• URL: http://arxiv.org/abs/2603.01260v1
• Date: Sun, 01 Mar 2026 20:33:19 GMT
• Title: MOSAIC: A Unified Platform for Cross-Paradigm Comparison and Evaluation of Homogeneous and Heterogeneous Multi-Agent RL, LLM, VLM, and Human Decision-Makers
• Authors: Abdulhamid M. Mousa, Yu Fu, Rakhmonberdi Khajiev, Jalaledin M. Azzabi, Abdulkarim M. Mousa, Peng Yang, Yunusa Haruna, Ming Liu,
• Abstract summary: Reinforcement learning (RL), large language models (LLMs), and vision-language models (VLMs) have been widely studied in isolation.<n>Existing infrastructure lacks the ability to deploy agents from different decision-making paradigms within the same environment.<n>We present MOSAIC, an open-source platform that bridges this gap by incorporating a diverse set of existing reinforcement learning environments.
• Score: 8.910641383873353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL), large language models (LLMs), and vision-language models (VLMs) have been widely studied in isolation. However, existing infrastructure lacks the ability to deploy agents from different decision-making paradigms within the same environment, making it difficult to study them in hybrid multi-agent settings or to compare their behaviour fairly under identical conditions. We present MOSAIC, an open-source platform that bridges this gap by incorporating a diverse set of existing reinforcement learning environments and enabling heterogeneous agents (RL policies, LLMs, VLMs, and human players) to operate within them in ad-hoc team settings with reproducible results. MOSAIC introduces three contributions. (i) An IPC-based worker protocol that wraps both native and third-party frameworks as isolated subprocess workers, each executing its native training and inference logic unmodified, communicating through a versioned inter-process protocol. (ii) An operator abstraction that forms an agent-level interface by mapping workers to agents: each operator, regardless of whether it is backed by an RL policy, an LLM, or a human, conforms to a minimal unified interface. (iii) A deterministic cross-paradigm evaluation framework offering two complementary modes: a manual mode that advances up to N concurrent operators in lock-step under shared seeds for fine-grained visual inspection of behavioural differences, and a script mode that drives automated, long-running evaluation through declarative Python scripts, for reproducible experiments. We release MOSAIC as an open, visual-first platform to facilitate reproducible cross-paradigm research across the RL, LLM, and human-in-the-loop communities.

Related papers

• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• PC2P: Multi-Agent Path Finding via Personalized-Enhanced Communication and Crowd Perception [12.114711272142031]
  PC2P is a novel distributed MAPF method derived from a Q-learning-based MARL framework.<n>We introduce a personalized-enhanced communication mechanism based on dynamic graph topology.<n>To resolve extreme deadlock issues, we propose a region-based deadlock-breaking strategy.
  arXiv  Detail & Related papers  (2026-01-06T03:11:26Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization [38.68388721203677]
  We propose CollabUIAgents, a multi-agent reinforcement learning framework with a novel multi-agent credit re-assignment strategy.<n>We show that our framework improves both performance and cross-environment generalizability of multi-agent systems.
  arXiv  Detail & Related papers  (2025-02-20T12:26:15Z)
• Cooperative Multi-Agent Planning with Adaptive Skill Synthesis [16.228784877899976]
  We present a novel multi-agent architecture that integrates vision-language models (VLMs) with a dynamic skill library and structured communication for decentralized closed-loop decision-making.<n>The skill library, bootstrapped from demonstrations, evolves via planner-guided tasks to enable adaptive strategies.<n>We demonstrate its strong performance against state-of-the-art MARL baselines across both symmetric and asymmetric scenarios.
  arXiv  Detail & Related papers  (2025-02-14T13:23:18Z)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Macro-Action-Based Multi-Agent/Robot Deep Reinforcement Learning under Partial Observability [4.111899441919164]
  State-of-the-art multi-agent reinforcement learning (MARL) methods have provided promising solutions to a variety of complex problems. We first propose a group of value-based RL approaches for MacDec-POMDPs. We formulate a set of macro-action-based policy gradient algorithms under the three training paradigms.
  arXiv  Detail & Related papers  (2022-09-20T21:13:51Z)
• MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning [61.28547338576706]
  Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms. We present MALib, a scalable and efficient computing framework for PB-MARL.
  arXiv  Detail & Related papers  (2021-06-05T03:27:08Z)

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.