The paper proposes Luar, a framework that trains reasoning language models to selectively use English translation only when their direct understanding of a non-English input is unreliable, significant…

The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…

The paper proposes an unsupervised Reinforcement Learning approach that enforces cross-lingual self-consistency to significantly enhance the multilingual reasoning capabilities of large language model…

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving state-of-the-art safety performance with massiv…

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving high safety performance with massive improvemen…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compress…

The paper proposes LaRA, a layer-wise representation analysis framework that detects data contamination in RL post-trained LLMs by analyzing geometric deviations across model layers.

The paper introduces Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…

The paper introduces Group Prioritized Off-Policy Optimization (POPO), a novel framework that efficiently accelerates RL finetuning for LLM reasoning by leveraging effective off-policy training batche…

The paper proposes SLAT, a segment-level adaptive trimming framework, which efficiently reduces redundant reasoning in large language model CoT outputs by selectively suppressing segments with low mar…

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a…

The paper introduces CosmicFish-HRM, a compact language model that achieves adaptive reasoning by dynamically allocating computational effort through a Hierarchical Reasoning Module (HRM), showing tha…

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

The paper introduces Temperature-Scaled On-Policy Self-Distillation (TS-OPSD), a novel method that internalizes temperature-based policy reheating into model parameters to combat entropy collapse in r…

The paper introduces Entropy-Cut Metropolis-Hastings, an efficient sampling method that uses next-token entropy to identify and resample from critical decision points in a reasoning trace, significant…