Related papers: MIND: Multi-agent inference for negotiation dialog…

Multi-agent systems have demonstrated exceptional performance in downstream tasks beyond diverse single agent baselines. A growing body of work has explored ways to improve their reasoning and collaboration, from vote, debate, to complex…

Persuasion, as one of the crucial abilities in human communication, has garnered extensive attention from researchers within the field of intelligent dialogue systems. We humans tend to persuade others to change their viewpoints, attitudes…

When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively…

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic…

Persuasive dialogue is central to human communication, yet existing datasets often rely on a single language model generating both roles, producing unrealistic interactions that violate the double-blind nature of persuasion. To overcome…

We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-box approaches, our courtroom-style…

Building a socially intelligent agent involves many challenges. One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate…

Multi-agent systems driven by large language models (LLMs) have shown promising abilities for solving complex tasks in a collaborative manner. This work considers a fundamental problem in multi-agent collaboration: consensus seeking. When…

Inspired by the dual-process theory of human cognition, we introduce DUMA, a novel conversational agent framework that embodies a dual-mind mechanism through the utilization of two generative Large Language Models (LLMs) dedicated to fast…

Social intelligence manifests the capability, often referred to as the Theory of Mind (ToM), to discern others' behavioral intentions, beliefs, and other mental states. ToM is especially important in multi-agent and human-machine…

Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in complex tasks. In this paper, we introduce MALT (Multi-Agent LLM…

Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonical testbed for agentic language models, requiring multi-turn interaction under hidden…

Natural language interaction with agentic Artificial Intelligence (AI), driven by Large Language Models (LLMs), is expected to remain a dominant paradigm in the near future. While humans instinctively align their communication with mental…

Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliable on complex tasks…

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small…

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…

A key challenge in transportation planning is that the collective preferences of heterogeneous travelers often diverge from the policies produced by model-driven decision tools. This misalignment frequently results in implementation delays…

Audio agents extend large audio-language models (LALMs) by decomposing audio questions into tool calls, intermediate evidence, and iterative reasoning steps. However, as LALMs become stronger, the key challenge shifts from enabling tool use…

While Large Language Models (LLMs) have shown remarkable advancements in reasoning and tool use, they often fail to generate optimal, grounded solutions under complex constraints. Real-world travel planning exemplifies these challenges,…

End-to-end multi-task dialogue systems are usually designed with separate modules for the dialogue pipeline. Among these, the policy module is essential for deciding what to do in response to user input. This policy is trained by…