Mixed SFT, a single supervised fine-tuning stage that jointly trains on no-CoT and long-CoT data, achieves a clearly higher post-RLVR performance ceiling than next-chunk reasoning RL while requiring over 60 times less training compute.
Abstract
Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reasoning-rich content but lack explicit chain-of-thought annotations. The method trains a model to generate implicit reasoning traces and rewards them by their ability to predict the next chunk of text. While promising, existing evaluations primarily compare against conventional SFT baselines, leaving open whether the gains come from the RL formulation itself or from more effectively exposing the model to no-CoT data. We address this question with a controlled study of next-chunk reasoning RL and a simple but previously overlooked alternative: Mixed SFT, a single supervised fine-tuning stage that jointly trains on no-CoT and long-CoT data. Despite its simplicity, Mixed SFT achieves a clearly higher post-RLVR performance ceiling than next-chunk reasoning RL while requiring over 60 times less training compute. The advantage is consistent across in-domain mathematical reasoning and out-of-domain reasoning tasks. Moreover, we show that higher pre-RLVR accuracy does not necessarily translate into higher post-RLVR accuracy, highlighting the need to evaluate no-CoT training strategies in the context of the full post-training pipeline.
I Reasoning via Multi-Teacher Distillation is proposed, a novel framework that 'compiles' the reasoning abilities of large teacher LLMs into a lightweight student Small Language Model (SLM), which significantly outperforms state-of-the-art baselines in both recommendation accuracy and inference efficiency.
Perception-RFT is introduced, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypassing intermediate reasoning tokens to directly align visual features with structured grounding outputs, and a reasoning variant under identical reward settings is constructed.
M. HarikrishnanP., G. Vignesh, Ganesh Parab et al.· arXiv.org· 0 citations
Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning capability. Such trajectories tend to be long due to complex, interwoven paths, which often include detours on the path toward the answer. However, it has been underexplored whether LLMs indeed benefit from learning complete trajectories in post-training, such as supervised fine-tuning (SFT). Starting from our pilot study, we find that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation. We analyze redundancy in reasoning trajectories through attention-based analyses and controlled token-removal studies, both of which show that intermediate tokens contribute minimally to final reasoning quality. This suggests that avoiding redundant information may allow LLMs to internally infer coherent alternatives by inferring missing steps from their internal knowledge, given known trajectory endpoints. Furthermore, we show that training LLMs using endpoints leads to consistent changes in reasoning behavior, and that it also benefits post-training methods based on reinforcement learning or on-policy distillation, highlighting the need to revisit complete reasoning traces. Code is available at https://github.com/naver-ai/revisiting-trace.
Jaehui Hwang, Sangdoo Yun, Byeongho Heo et al.· 0 citations
It is suggested that using standard CoT prompting increasingly acts as a source of distraction as models grow stronger, because standard CoT prompting also demands style adaptation, formatting compliance, and potentially undesired contextualization, which can distract models from the core reasoning task.
Denys Pushkin, Albert Q. Jiang, Aryo Lotfi et al.· 0 citations
Paired runs of the same question at matched reasoning horizons across 198 GPQA Diamond and 500 MMLU-Pro questions are evaluated, finding that a tight deadline can favor lower effort or a concise instruction, whereas allowing high effort to finish can recover higher final accuracy.
Francesca Carlon, Vincent Ginis, A. Algaba· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
