相关论文: Reflection in the Dark: Exposing and Escaping the …

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Parallel test-time scaling typically trains separate generation and verification models, incurring high training and inference costs. We propose Advantage Decoupled Preference Optimization (ADPO), a unified reinforcement learning framework…

Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is…

Training data quality is one of the most important drivers of final model quality. In this work, we introduce a method for evaluating data integrity based on the assumption that low-quality input prompts result in high variance and low…

Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…

We propose Multi Agent Reflective Policy Optimization (MARPO) to alleviate the issue of sample inefficiency in multi agent reinforcement learning. MARPO consists of two key components: a reflection mechanism that leverages subsequent…

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop.…

Large Language Models (LLMs) often suffer from mode collapse, repeatedly generating the same few completions even when many valid answers exist, limiting their diversity across a wide range of tasks. We introduce Group-Aware Policy…

Argument mining (AM) is an interdisciplinary research field focused on the automatic identification and classification of argumentative components, such as claims and premises, and the relationships between them. Recent advances in large…

Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task success rather than the target semantic predicate. Using agentic compile-fix as the…

The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models…

Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with verifiable rewards (RLVR) learn only from a scalar outcome…

Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are…

LLMs have demonstrated strong performance in data-rich domains such as programming, yet their reliability in engineering tasks remains limited. Circuit analysis--requiring multimodal understanding and precise mathematical…

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored…

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…