Related papers: WebAnchor: Anchoring Agent Planning to Stabilize L…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance…

Agentic Reinforcement Learning (Agentic RL) has shown remarkable potential in large language model-based (LLM) agents. These works can empower LLM agents to tackle complex tasks via multi-step, tool-integrated reasoning. However, an…

Effective information seeking in the vast and ever-growing digital landscape requires balancing expansive search with strategic reasoning. Current large language model (LLM)-based agents struggle to achieve this balance due to limitations…

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff''…

Large reasoning models have demonstrated strong problem-solving abilities, yet real-world tasks often require external tools and long-horizon interactions. Existing agent frameworks typically follow predefined workflows, which limit…

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior…

Large Language Model (LLM) agents have recently shown strong potential in domains such as automated coding, deep research, and graphical user interface manipulation. However, training them to succeed on long-horizon, domain-specialized…

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…

Large Language Model (LLM)-based web agents excel at knowledge-intensive tasks but face a fundamental conflict between the need for extensive exploration and the constraints of limited context windows. Current solutions typically rely on…

Recent advancements in large language models (LLMs) have enabled understanding webpage contexts, product details, and human instructions. Utilizing LLMs as the foundational architecture for either reward models or policies in reinforcement…

Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority.…

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct…