A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
K. Murphy
A comprehensive overview of deep reinforcement learning and sequential decision making, covering value-based, policy-based, model-based, multi-agent, and LLM-related methods.
Adam Kostka, J. Chudziak
This paper introduces a novel multi-agent architecture integrating Theory of Mind, BDI-style internal beliefs, and symbolic solvers to improve collaborative decision-making in LLM-based systems.
Nuo Chen, Yicheng Tong, Yuzhe Yang, et al.
This paper systematically studies diversity collapse in multi-agent LLMs, showing that interaction structures, not model insufficiency, primarily cause reduced exploration diversity.
Reza Olfati‐Saber
A theoretical framework for distributed flocking algorithms that achieve collective behavior without leaders, validated through simulations of hundreds of agents.
Xinyi Li, S. Wang, Siqi Zeng, et al.
A comprehensive survey of LLM-based multi-agent systems, proposing a unified five-component workflow framework and reviewing applications in problem-solving and world simulation.
Chidaksh Ravuru, Sakhinana Sagar Srinivas, Venkataramana Runkana
Proposes an agentic Retrieval-Augmented Generation framework with hierarchical multi-agent architecture for time series analysis, achieving state-of-the-art performance.
Junsol Kim, Shiyang Lai, Nino Scherrer, et al.
Reasoning models outperform instruction-tuned models not by longer chains of thought but by simulating multi-agent-like interactions that diversify and debate internal cognitive perspectives.
Ruicheng Ao, Siyang Gao, David Simchi-Levi
This paper establishes fundamental reliability limits of LLM-based multi-agent planning by modeling it as a delegated decision network and proving it is dominated by a centralized Bayes decision maker.
Unknown
Proposes a multi-agent debate framework where multiple language models iteratively critique and refine answers to improve factual accuracy and reasoning.
Linjun Li
LLMs can appear safer under direct dangerous objectives than when mediated by other agents, revealing a compositional safety gap.
Hongxin Zhang, Chunru Lin, Junyan Li, et al.
GS-Agent is a multi-agent framework that automates the creation of physically plausible 4D worlds from natural language by integrating physics engines and emulating human workflows.
Unknown
This paper uses language models to enable long-horizon planning for multi-agent robots in partially observable environments, overcoming traditional RL and HRL limitations.