Related papers: FoldAct: Efficient and Stable Context Folding for …

Conventional Retrieval-Augmented Generation (RAG) systems often struggle with complex multi-hop queries over long documents due to their single-pass retrieval. We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware…

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed generation: long-tailed trajectories indispensable for model…

Hierarchical Reinforcement Learning algorithms have successfully been applied to temporal credit assignment problems with sparse reward signals. However, state-of-the-art algorithms require manual specification of sub-task structures, a…

Reinforcement Learning (RL) offers a promising framework for autonomous driving by enabling agents to learn control policies through interaction with environments. However, large and high-dimensional action spaces often used to support…

We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as a matter of…

Large language models (LLMs) often struggle to accurately read and comprehend extremely long texts. Current methods for improvement typically rely on splitting long contexts into fixed-length chunks. However, fixed truncation risks…

As the number of spacecraft in orbit continues to increase, it is becoming more challenging for human operators to manage each mission. As a result, autonomous control methods are needed to reduce this burden on operators. One method of…

Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency bottleneck, mainly arising from the long-tail bubbles across…

As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignment and exploration become more challenging, and the long planning horizon hinders mode discovery…

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from…

Large language model (LLM) agents typically rely on reactive decision-making paradigms such as ReAct, selecting actions conditioned on growing execution histories. While effective for short tasks, these approaches often lead to redundant…

Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents…

Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts…

Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal…

Recent efforts have augmented language models (LMs) with external tools or environments, leading to the development of language agents that can reason and act. However, most of these agents rely on few-shot prompting techniques with…