Related papers: Better LLM Reasoning via Dual-Play

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in their production of reasoning traces. Even when tasked with non-English problems, these models…

Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult…

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily…

Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly…

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than…

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models…

Process Reward Models (PRMs) enhance reasoning ability of LLMs by providing step-level supervision. However, their widespread adoption is limited due to expensive manual step-level annotation and poor generalization of static training data…

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm,…

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Large language models (LLMs) have significantly transformed the educational landscape. As current plagiarism detection tools struggle to keep pace with LLMs' rapid advancements, the educational community faces the challenge of assessing…

Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from calibration degeneration, where models become excessively over-confident in incorrect answers.…

Reasoning models excel in complex problem solving but exhibit a concerning trade off between reasoning capabilities and instruction following abilities. Existing approaches for improving instruction following rely on stronger external…

In this work, we aim to incentivize the reasoning ability of Multimodal Large Language Models (MLLMs) via reinforcement learning (RL) and develop an effective approach that mitigates the sparse reward and advantage vanishing issues during…

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues…

Safety alignment is critical in pre-training large language models (LLMs) to generate responses aligned with human values and refuse harmful queries. Unlike LLM, the current safety alignment of VLMs is often achieved with post-hoc safety…

Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) remains constrained by data saturation and performance…

Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability. Prior works have explored prompt evolving, but are…