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

Large language models demonstrate remarkable reasoning capabilities but often produce unreliable or incorrect responses. Existing verification methods are typically model-specific or domain-restricted, requiring significant computational…

Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using feedback to guide future search. However, existing methods are…

Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is…

Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks. However, designing effective evolving methods for instruction evolution requires substantial human expertise.…

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn…

Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with its value function. Our key insight is that one can treat…

Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…

We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the environments that train it. In zero-data reasoning RL, this reframes self-improvement from a…

Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and…

Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…

Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats…

Retrieval-augmented generation (RAG) grounds large language models (LLMs) in up-to-date external evidence, yet existing multi-hop RAG pipelines still issue redundant subqueries, explore too shallowly, or wander through overly long search…

Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic…

Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians sequentially ask questions and order tests to strategically…

Exploration is essential for general-purpose robotic learning, especially in open-ended environments where dense rewards, explicit goals, or task-specific supervision are scarce. Vision-language models (VLMs), with their semantic reasoning…

Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings…

In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow,…

Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller…

Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While…