Related papers: ExpSeek: Self-Triggered Experience Seeking for Web…

Web AI agents such as ChatGPT Agent and GenSpark are increasingly used for routine web-based tasks, yet they still rely on text-based input prompts, lack proactive detection of user intent, and offer no support for interactive data analysis…

Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and updated, while paying less attention to how experience should…

The recent surge in research interest in applying large language models (LLMs) to decision-making tasks has flourished by leveraging the extensive world knowledge embedded in LLMs. While there is a growing demand to tailor LLMs for custom…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances this process by introducing autonomous LLM agents into the…

Addressing intricate real-world problems necessitates in-depth information seeking and multi-step reasoning. Recent progress in agentic systems, exemplified by Deep Research, underscores the potential for autonomous multi-step research. In…

Search agents have achieved significant advancements in enabling intelligent information retrieval and decision-making within interactive environments. Although reinforcement learning has been employed to train agentic models capable of…

This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from…

Building Large Language Model agents that expand their capabilities by interacting with external tools represents a new frontier in AI research and applications. In this paper, we introduce InfoAgent, a deep research agent powered by an…

Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques. However, effectively enabling LLMs to seek accurate knowledge in complex tasks remains a challenge due to the complexity…

Information processing tasks involve complex cognitive mechanisms that are shaped by various factors, including individual goals, prior experience, and system environments. Understanding such behaviors requires a sophisticated and…

Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable enough to be deployed in real, user-facing, applications.…

General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…

Empathy is fundamental to human interactions, yet it remains unclear whether embodied agents can provide human-like empathetic support. Existing works have studied agents' tasks solving and social interactions abilities, but whether agents…

Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development. Addressing this challenge, we envision a recommendation…

Developing autonomous agents that quickly explore an environment and adapt their behavior online is a canonical challenge in robotics and machine learning. While humans are able to achieve such fast online exploration and adaptation, often…

Optimizing and refining action execution through exploration and interaction is a promising way for robotic manipulation. However, practical approaches to interaction-driven robotic learning are still underexplored, particularly for…

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Deep research systems powered by LLM agents have transformed complex information seeking by automating the iterative retrieval, filtering, and synthesis of insights from massive-scale web sources. However, existing systems predominantly…