Related papers: Stay Focused: Problem Drift in Multi-Agent Debate

Large language models are increasingly integrated into decision-making in areas such as healthcare, law, finance, engineering, and government. Yet they share a critical limitation: they produce fluent outputs even when their internal…

Writing persuasive arguments is a challenging task for both humans and machines. It entails incorporating high-level beliefs from various perspectives on the topic, along with deliberate reasoning and planning to construct a coherent…

Remarkable performance of large language models (LLMs) in a variety of tasks brings forth many opportunities as well as challenges of utilizing them in production settings. Towards practical adoption of LLMs, multi-agent systems hold great…

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…

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…

Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we…

Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its performance. Therefore, maintaining a constant monitoring…

Multi-task learning has recently become a very active field in deep learning research. In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks…

We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…

Concept drift is a major issue that greatly affects the accuracy and reliability of many real-world applications of machine learning. We argue that to tackle concept drift it is important to develop the capacity to describe and analyze it.…

Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates diverse peer perspectives to make a final decision. Drawing inspiration from social…

Large language models (LLMs) are increasingly used as judges to evaluate agent performance, particularly in non-verifiable settings where judgments rely on agent trajectories including chain-of-thought (CoT) reasoning. This paradigm…

Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction…

Context: Large Language Model (LLM) agents are becoming widely used for various Requirements Engineering (RE) tasks. Research on improving their accuracy mainly focuses on prompt engineering, model fine-tuning, and retrieval augmented…

This paper introduces a Theory of Troubleshooting that is rooted in cognitive science. This theory helps software developers explain the challenges they face and the project risks that emerge as troubleshooting becomes difficult. We define…

We investigate whether and where multi-task learning (MTL) can improve performance on NLP problems related to argumentation mining (AM), in particular argument component identification. Our results show that MTL performs particularly well…

This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to…

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…

As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent.…

Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the…