Related papers: Toward Scalable Verifiable Reward: Proxy State-Bas…

Large language models (LLMs) remain unreliable for high-stakes claim verification due to hallucinations and shallow reasoning. While retrieval-augmented generation (RAG) and multi-agent debate (MAD) address this, they are limited by…

Recommender systems (RecSys) are widely used across various modern digital platforms and have garnered significant attention. Traditional recommender systems usually focus only on fixed and simple recommendation scenarios, making it…

We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their…

Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent frameworks are typically limited to a small set of pre-defined…

Agent-based simulation is crucial for modeling complex human behavior, yet traditional approaches require extensive domain knowledge and large datasets. In data-scarce healthcare settings where historic and counterfactual data are limited,…

Tool-augmented Large Language Models (TaLLMs) extend LLMs with the ability to invoke external tools, enabling them to interact with real-world environments. However, a major limitation in deploying TaLLMs in sensitive applications such as…

LLM agents are increasingly expected to function as general-purpose systems capable of resolving open-ended user requests. While existing benchmarks focus on domain-aware environments for developing specialized agents, evaluating…

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time. Existing…

Large Language Models (LLMs) have achieved impressive results in knowledge-based Visual Question Answering (VQA). However existing methods still have challenges: the inability to use external tools autonomously, and the inability to work in…

A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models, specifically LLMs, by analyzing their outputs. An LLM as judge is the combination of one model and one specifically engineered judge prompt…

The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction.…

Predictive analysis is a cornerstone of modern decision-making, with applications in various domains. Large Language Models (LLMs) have emerged as powerful tools in enabling nuanced, knowledge-intensive conversations, thus aiding in complex…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential application of Large Language Models (LLMs) as symbolic…

Recommender systems are essential components of many online platforms, yet traditional approaches still struggle with understanding complex user preferences and providing explainable recommendations. The emergence of Large Language Model…

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…

Testing conversational AI systems at scale across diverse domains necessitates realistic and diverse user interactions capturing a wide array of behavioral patterns. We present a novel multi-agent framework for realistic, explainable human…

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…

Tool use in stateful environments presents unique challenges for large language models (LLMs), where existing test-time compute strategies relying on repeated trials in the environment are impractical. We propose dynamics modelling (DyMo),…