Related papers: Bootstrapping Exploration with Group-Level Natural…

Retrieval-Augmented Generation (RAG) integrates external knowledge with Large Language Models (LLMs) to enhance factual correctness and mitigate hallucination. However, dense retrievers often become the bottleneck of RAG systems due to…

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

Policy exploration is critical in reinforcement learning (RL), where existing approaches include greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately applied in all kinds of…

Generative artificial intelligence (AI), in particular large language models (LLMs), is poised to drive transformative economic change. LLMs are pre-trained on vast text data to learn general language patterns, but a subsequent…

Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lean toward exploitation, and increasingly encounter…

As retrieval-augmented generation (RAG) becomes more widespread, the role of retrieval is shifting from retrieving information for human browsing to retrieving context for AI reasoning. This shift creates more complex search environments,…

Reward engineering has long been a challenge in Reinforcement Learning (RL) research, as it often requires extensive human effort and iterative processes of trial-and-error to design effective reward functions. In this paper, we propose…

This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize the retrieval models…

Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, lack of interpretability, and sparse supervision signals. To…

Reinforcement learning (RL) has demonstrated significant promise in enhancing the reasoning capabilities of Text2SQL LLMs, especially with advanced algorithms such as GRPO and DAPO. However, the performance of these methods is highly…

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user…

Reinforcement learning (RL) is one of the three basic paradigms of machine learning. It has demonstrated impressive performance in many complex tasks like Go and StarCraft, which is increasingly involved in smart manufacturing and…

Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on constructing extensive domain-specific datasets to train…

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful…

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool…

Reinforcement learning (RL) with outcome-based rewards has proven effective for improving large language models (LLMs) on complex reasoning tasks. However, its success often depends on the base model occasionally sampling correct solutions.…

Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a wide range of tasks. We introduce Group-Aware Policy…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert…