Related papers: Think, Speak, Decide: Language-Augmented Multi-Age…

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

This paper pioneers a novel approach to economic and public policy analysis by leveraging multiple Large Language Models (LLMs) as heterogeneous artificial economic agents. We first evaluate five LLMs' economic decision-making capabilities…

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…

Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving…

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off:…

Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is…

Within the domain of Massively Multiplayer Online (MMO) economy research, Agent-Based Modeling (ABM) has emerged as a robust tool for analyzing game economics, evolving from rule-based agents to decision-making agents enhanced by…

Current large reasoning models (LRMs) have shown strong ability on challenging tasks after reinforcement learning (RL) based post-training. However, previous work mainly focuses on English reasoning in expectation of the strongest…

Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…

Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…

Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that…

Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Large language models (LLMs) fine-tuned on multimodal financial data have demonstrated impressive reasoning capabilities in various financial tasks. However, they often struggle with multi-step, goal-oriented scenarios in interactive…

While Large Language Models (LLMs) have shown impressive capabilities in numerous Natural Language Processing (NLP) tasks, they still struggle with financial question answering (QA), particularly when numerical reasoning is required.…

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling…

Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is…

Large language models (LLMs) excel in natural language generation but often confidently produce incorrect responses, especially in tasks like mathematical reasoning. Chain-of-thought prompting, self-verification, and multi-agent debate are…