MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration

arXiv:2603.01260 · cs.LG, cs.AI · Submitted 2026-03-01 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-03-01

Updated: 2026-09-10

Comments: 4 pages, 2 figures

Code: https://github.com/Abdulhamid97Mousa/MOSAIC

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 16× in this paper · explained in 4 episodes
• Large Language Model — 8× in this paper
• Action Space — 7× in this paper · explained in 1 episode
• Benchmark — 7× in this paper · explained in 2 episodes
• Benchmarking — 6× in this paper · explained in 3 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Ad Hoc Teamwork — 4× in this paper · explained in 1 episode
• Vision-Language Model — 4× in this paper
• Human-in-the-Loop — 3× in this paper · explained in 3 episodes
• Multi-Agent System — 3× in this paper · explained in 5 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Cooperation — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 24 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes

Sources

• An Introduction to Vision-Language Modeling
• Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play
• GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents
• TextArena
• Acme: A Research Framework for Distributed Reinforcement Learning
• lmgame-Bench: How Good are LLMs at Playing Games?
• OpenRL: A Unified Reinforcement Learning Framework
• LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
• BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors
• TextAtari: 100K Frames Game Playing with Language Agents
• LLM-PySC2: Starcraft II learning environment for Large Language Models
• XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
• BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
• PettingZoo: Gym for Multi-Agent Reinforcement Learning
• Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboard
• Atari-GPT: Benchmarking Multimodal Large Language Models as Low-Level Policies in Atari Games
• AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
• CREW: Facilitating Human-AI Teaming Research
• MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks