Related papers: EVE-Agent: Evidence-Verifiable Self-Evolving Agent…

Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the…

The application of advanced generative artificial intelligence in education is often constrained by the lack of real-time adaptability, personalization, and reliability of the content. To address these challenges, we propose ExpertAgent -…

Automating scientific discovery in complex, experiment-driven domains requires more than iterative mutation of programs; it demands structured hypothesis management, environment interaction, and principled reflection. We present OR-Agent, a…

The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective…

Although the effectiveness of Large Language Models (LLMs) as judges (LLM-as-a-judge) has been validated, their performance remains limited in open-ended tasks, particularly in story evaluation. Accurate story evaluation is crucial not only…

Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts, object states, and other execution factors, these skills…

The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective…

Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas…

Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning. Although recent work explores various forms of reward shaping and step-level…

Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction…

LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts often do not reveal why an agent's stance changes: movement…

Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement. Recent…

When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…

Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability. Prior works have explored prompt evolving, but are…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

Determining the veracity of atomic claims is an imperative component of many recently proposed fact-checking systems. Many approaches tackle this problem by first retrieving evidence by querying a search engine and then performing…

Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs,…

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…