Related papers: Align While Search: Belief-Guided Exploratory Infe…

Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted…

We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed…

Active reasoning requires large language model (LLM) agents to interact with external sources and strategically gather information to solve problems in multiple turns. Central to this process is belief tracking: maintaining an accurate…

Agentic search, as a more autonomous and adaptive paradigm of retrieval augmentation, is driving the evolution of intelligent search systems. However, existing evaluation frameworks fail to align well with the goals of agentic search.…

Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but…

Despite their success in many domains, large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. This is crucial as many real-world applications, ranging from personalized…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…

Embeddings extracted by pre-trained Large Language Models (LLMs) have significant potential to improve information retrieval and search. Beyond the zero-shot setup in which they are being conventionally used, being able to take advantage of…

This paper presents an innovative large language model (LLM) agent framework for enhancing diagnostic accuracy in simulated clinical environments using the AgentClinic benchmark. The proposed automatic correction enables doctor agents to…

While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in…

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Effective training-time guidance is central to multi-agent reinforcement learning (MARL), yet remains difficult in sparse-reward settings where weak supervision limits coordination and policy improvement, and existing methods often require…

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit this bottleneck through the lens of speculation. While…

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

Sequential planning in large state space and action space quickly becomes intractable due to combinatorial explosion of the search space. Heuristic methods, like monte-carlo tree search, though effective for large state space, but struggle…

Classical models of opinion dynamics assume human participants with bounded rationality and limited coordination. The rise of LLM-based agents introduces a qualitative shift: agents can now participate in online discussions at scale,…

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…