相关论文: Resolving Action Bottleneck: Agentic Reinforcement…

Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value…

Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully…

While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing…

Reinforcement learning means learning a policy--a mapping of observations into actions--based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with…

Large reasoning models trained with reinforcement learning and verifiable rewards (RLVR) achieve strong performance on complex reasoning tasks, yet often overthink, generating redundant reasoning without performance gains. Existing…

Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave perception-related tokens, which ground visual content, with…

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…

Large Language Models (LLMs) perform well in language tasks but often lack collaborative awareness and struggle to optimize global performance in multi-agent settings. We present a reinforcement learning-augmented LLM agent framework that…

Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same…

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a…

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically…

Reinforcement learning is a machine learning approach based on behavioral psychology. It is focused on learning agents that can acquire knowledge and learn to carry out new tasks by interacting with the environment. However, a problem…

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy…

Traditional agentic workflows rely on external prompts to manage interactions with tools and the environment, which limits the autonomy of reasoning models. We position \emph{Large Agent Models (LAMs)} that internalize the generation of…

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully reflects the processes underlying the model's final answer,…

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language tokens with continuous latent tokens. These methods consume fewer tokens…

Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an…