Related papers: Debating the Unspoken: Role-Anchored Multi-Agent R…

Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models, yet its effectiveness remains limited in complex, multi-step reasoning scenarios. Recent efforts have incorporated…

Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority…

We propose a novel method for fact-checking on knowledge graphs based on debate dynamics. The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments…

Multi-agent debate often wastes compute by using a fixed adversarial stance, aggregating without deliberation, or stopping on heuristics. We introduce MACI, an active controller with two independent dials that decouple information from…

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack…

Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models…

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…

The task of joint dialog sentiment classification (DSC) and act recognition (DAR) aims to simultaneously predict the sentiment label and act label for each utterance in a dialog. In this paper, we put forward a new framework which models…

Transformer models have demonstrated exceptional performance across a wide range of applications. Though forming the foundation of Transformer models, the dot-product attention does not scale well to long-context data since its time…

Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high…

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…

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising…

While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Current systems typically rely on persona-agnostic summarization, which records facts…

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or…

Amodal completion, the task of inferring invisible object parts, faces significant challenges in maintaining semantic consistency and structural integrity. Prior progressive approaches are inherently limited by inference instability and…

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.…

Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment, including automated fact-checking and claim verification…

We study the problem of automatic fact-checking, paying special attention to the impact of contextual and discourse information. We address two related tasks: (i) detecting check-worthy claims, and (ii) fact-checking claims. We develop…

Equipping agents with the capacity to justify made decisions using supporting evidence represents a cornerstone of accountable decision-making. Furthermore, ensuring that justifications are in line with human expectations and societal norms…

Task-oriented dialogue systems are essential for applications ranging from customer service to personal assistants and are widely used across various industries. However, developing effective multi-domain systems remains a significant…