Related papers: TreePS-RAG: Tree-based Process Supervision for Rei…

Reinforcement Learning (RL) serves as a potent paradigm for enhancing reasoning capabilities in Large Language Models (LLMs), yet standard outcome-based approaches often suffer from reward sparsity and inefficient credit assignment. In this…

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

Enabling humans to identify potential flaws in an agent's decision making is an important Explainable AI application. We consider identifying such flaws in a planning-based deep reinforcement learning (RL) agent for a complex real-time…

Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-horizon reasoning tasks. Agentic Reinforcement Learning…

In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round…

Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a…

Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global…

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…

Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG systems still produce incorrect answers in many cases. Why…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned…

Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-first training framework…

Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works scale RAG at inference time along two…

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

While Retrieval Augmented Generation (RAG) is now widely adopted to enhance LLMs, evaluating its true performance benefits in a reproducible and interpretable way remains a major hurdle. Existing methods often fall short: they lack domain…

Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often…

Embodied Everyday Task is a popular task in the embodied AI community, requiring agents to make a sequence of actions based on natural language instructions and visual observations. Traditional learning-based approaches face two challenges.…

Frontier language models have demonstrated strong reasoning and long-horizon tool-use capabilities. However, existing RAG systems fail to leverage these capabilities. They still rely on two paradigms: (1) designing an algorithm that…

Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide reasoning traces. However, current KG-RAG systems often rely…

The performance of language models is commonly limited by insufficient knowledge and constrained reasoning. Prior approaches such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) address these issues by incorporating…