Related papers: VAPO: Efficient and Reliable Reinforcement Learnin…

Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…

In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinforce desired behaviors. Recent research has introduced…

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

Large Vision-Language Models (LVLMs) have become powerful general-purpose assistants, yet their predictions often lack reliability and interpretability due to insufficient grounding in visual evidence. The emerging thinking-with-images…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible…

Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions -- has achieved remarkable progress through reinforcement learning (RL). However,…

Agentic vision-language models are increasingly trained to "think with images" by calling image operations. However, we show that high final-answer accuracy often hides unfaithful visual reasoning: models may invoke tools on irrelevant…

We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuning (SFT) followed by reinforcement learning (RL). A central…

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative…

Scaling test-time compute is crucial for enhancing the reasoning capabilities of large language models (LLMs). Existing approaches typically employ reinforcement learning (RL) to maximize a verifiable reward obtained at the end of reasoning…

Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train…

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like mathematical reasoning and code generation. However, directly…

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…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only as the very last…