Related papers: BAR: A Backward Reasoning based Agent for Complex …

We present APT, an advanced Large Language Model (LLM)-driven framework that enables autonomous agents to construct complex and creative structures within the Minecraft environment. Unlike previous approaches that primarily concentrate on…

Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with a user. However, most current systems treat dialogue reactively and lack a principled mechanism to…

Recent embodied agents are primarily built based on reinforcement learning (RL) or large language models (LLMs). Among them, RL agents are efficient for deployment but only perform very few tasks. By contrast, giant LLM agents (often more…

Recent advancements in Large Language Model~(LLM)-based Multi-Agent Systems (MAS) have demonstrated remarkable potential for tackling complex decision-making tasks. However, existing frameworks inevitably rely on serialized execution…

With the rise of artificial intelligence (AI), applying large language models (LLMs) to mathematical problem-solving has attracted increasing attention. Most existing approaches attempt to improve Operations Research (OR) optimization…

Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various…

Large Language Model (LLM)-powered Multi-agent systems (MAS) have achieved state-of-the-art results on various complex reasoning tasks. Recent works have proposed techniques to automate the design of MASes, eliminating the need for manual…

Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects a fundamental…

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…

As Large Language Models (LLMs) gain agentic abilities, they will have to navigate complex multi-agent scenarios, interacting with human users and other agents in cooperative and competitive settings. This will require new reasoning skills,…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

In open-world environments like Minecraft, existing agents face challenges in continuously learning structured knowledge, particularly causality. These challenges stem from the opacity inherent in black-box models and an excessive reliance…

Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from…

Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios. While MuZero enables effective model learning…

Collaboration is ubiquitous and essential in day-to-day life -- from exchanging ideas, to delegating tasks, to generating plans together. This work studies how LLMs can adaptively collaborate to perform complex embodied reasoning tasks. To…

Many reinforcement learning environments (e.g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values. The challenge in exploration efficiency in such environments makes it difficult for…

Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…