Related papers: From Reasoning to Agentic: Credit Assignment in Re…

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in…

Recent work, spanning from autonomous vehicle coordination to in-space assembly, has shown the importance of learning collaborative behavior for enabling robots to achieve shared goals. A common approach for learning this cooperative…

Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face…

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, they struggle in open-ended and…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning (RL)-based fine-tuning is a key mechanism for improvement, but its effectiveness is…

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous,…

The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience.…