Related papers: GRPO-CARE: Consistency-Aware Reinforcement Learnin…

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities but often struggle with complex, multi-step mathematical reasoning, where minor errors in visual perception or logical deduction can lead to complete failure.…

Large language models (LLMs) hold transformative potential for medical decision support yet their application in psychiatry remains constrained by hallucinations and superficial reasoning. This limitation is particularly acute in…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emerging as a leading approach. However, GRPO and its variants are…

DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unfaithful reasoning and degrading under small causal…

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.…

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or…

Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to compliance rules. We propose…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Recent advances in reinforcement learning (RL) using numerical rewards have significantly enhanced the complex reasoning capabilities of large language models (LLMs). However, we identify three fundamental limitations of purely numerical…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human annotations are scarce and subjective, reward models are vulnerable to reward hacking, and…

Through reinforcement learning with verifiable rewards (RLVR), large language models have achieved substantial progress in domains with easily verifiable outcomes, such as mathematics and coding. However, when applied to more complex tasks…

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while…

Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforcement learning (RL). This separation creates a complex, resource-intensive pipeline and…

Recently, online Reinforcement Learning with Verifiable Rewards (RLVR) has become a key paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically treat all training samples…