Related papers: ARM: Advantage Reward Modeling for Long-Horizon Ma…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning.…

Recent embodied agents are primarily built based on reinforcement learning (RL) or large language models (LLMs). Among them, RL agents are efficient for deployment but only perform very few tasks. By contrast, giant LLM agents (often more…

Recent studies show that Large Language Models (LLMs) achieve strong reasoning capabilities through supervised fine-tuning or reinforcement learning. However, a key approach, the Process Reward Model (PRM), suffers from reward hacking,…

The reward model has become increasingly important in alignment, assessment, and data construction for large language models (LLMs). Most existing researchers focus on enhancing reward models through data improvements, following the…

LLM-based (Large Language Model) GUI (Graphical User Interface) agents can potentially reshape our daily lives significantly. However, current LLM-based GUI agents suffer from the scarcity of high-quality training data owing to the…

Standard reinforcement learning (RL) algorithms assume that the observation of the next state comes instantaneously and at no cost. In a wide variety of sequential decision making tasks ranging from medical treatment to scientific…

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…

Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Relative Policy Optimization (GRPO) have shown promise in this…

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively…

Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However,…

This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM,…

Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…

Autonomous race driving poses a complex control challenge as vehicles must be operated at the edge of their handling limits to reduce lap times while respecting physical and safety constraints. This paper presents a novel reinforcement…

Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. Generally, neural network based ARMs are designed to allow fast inference, but sampling from these models is…

This paper considers multi-agent reinforcement learning (MARL) where the rewards are received after delays and the delay time varies across agents and across time steps. Based on the V-learning framework, this paper proposes MARL algorithms…

We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained…

Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT…