Related papers: TeamTR: Trust-Region Fine-Tuning for Multi-Agent L…

Complex medical reasoning has historically required frontier language models to achieve clinically-acceptable accuracy, creating computational barriers that limit deployment in resource-constrained clinical settings. We present…

Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge acquisition, reasoning, and tool use, making them promising candidates for autonomous agent applications. However, training LLM agents for complex…

Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the…

As multi-agent Large Language Model (LLM) systems scale, evaluating their emergent coordination dynamics becomes increasingly critical. However, current evaluation paradigms-focused on single agents or small, explicitly structured…

This survey investigates foundational technologies essential for developing effective Large Language Model (LLM)-based multi-agent systems. Aiming to answer how best to optimize these systems for collaborative, dynamic environments, we…

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…

We propose a framework for the decentralized control of a team of agents that are assigned local tasks expressed as Linear Temporal Logic (LTL) formulas. Each local LTL task specification captures both the requirements on the respective…

The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological…

In Agentic AI, Large Language Models (LLMs) are increasingly used in the orchestration layer to coordinate multiple agents and to interact with external services, retrieval components, and shared memory. In this setting, failures are not…

An often neglected issue in multi-agent reinforcement learning (MARL) is the potential presence of unreliable agents in the environment whose deviations from expected behavior can prevent a system from accomplishing its intended tasks. In…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either…

Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…

Multi-robot task planning requires decomposing natural-language instructions into executable actions for heterogeneous robot teams. Conventional Planning Domain Definition Language (PDDL) planners provide rigorous guarantees but struggle to…

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with…

Multi-step tool orchestration remains challenging for LLMs, as state-of-the-art models frequently fail on full sequence execution due to parameter errors. Training for these workflows faces two obstacles: the lack of environments supporting…

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and…

Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…