Related papers: PABU: Progress-Aware Belief Update for Efficient L…

Large language models (LLMs) have been successfully adapted for interactive decision-making tasks like web navigation. While achieving decent performance, previous methods implicitly assume a forward-only execution mode for the model, where…

Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-level annotations of every user utterance. In this paper we aim…

While large language models have made significant progress in mathematical reasoning, they remain unreliable at judging the correctness of their own solutions. Existing approaches that equip models with self-verification typically treat…

LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably contain ambiguities and logical or semantic gaps that cause…

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation, yet existing research has mostly evaluated their adherence to…

Reinforcement Learning (RL) has shown great potential for autonomous decision-making in the cybersecurity domain, enabling agents to learn through direct environment interaction. However, RL agents in Autonomous Cyber Operations (ACO)…

Large language model (LLM)-powered multi-agent systems (MAS) demonstrate remarkable collective intelligence, wherein multi-agent memory serves as a pivotal mechanism for continual adaptation. However, existing multi-agent memory designs…

Predicting human decision-making in high-stakes environments remains a central challenge for artificial intelligence. While large language models (LLMs) demonstrate strong general reasoning, they often struggle to generate consistent,…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exploration and statistics of existing peer review data, which do not adequately address the…

As LLM-based agents operate over sequential multi-step reasoning, hallucinations arising at intermediate steps risk propagating along the trajectory, thus degrading overall reliability. Unlike hallucination detection in single-turn…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks assign tasks based on predefined roles without considering whether an agent can accurately…

We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from…

Large language models (LLMs) that iteratively revise their outputs through mechanisms such as chain-of-thought reasoning, self-reflection, or multi-agent debate lack principled guarantees regarding the stability of their probability…

Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…

The recent advancements of Large Language Models (LLMs) have spurred considerable research interest in extending their linguistic capabilities beyond text to other modalities, which leads to emergence of speech-based LLMs (SpeechLMs) with…

Social biases and belief-driven behaviors can significantly impact Large Language Models (LLMs) decisions on several tasks. As LLMs are increasingly used in multi-agent systems for societal simulations, their ability to model fundamental…

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous…

Large language models (LLMs) perform substantially below human level on existing theory-of-mind (ToM) benchmarks, even when augmented with chain-of-thought prompting or probabilistic belief updates. We argue that these failures primarily…