Echo-GRPO is proposed, a framework that lets the model reason in the words it speaks, and idiolectal paraphrasing is a plug-in module that consistently improves both RL and supervised fine-tuning frameworks for reasoning distillation, demonstrating that policy-aligned supervision extends beyond GRPO.
Abstract
Recent large language models achieve strong performance on complex reasoning tasks, where reinforcement learning with Group Relative Policy Optimization (GRPO) has emerged as a leading paradigm for optimizing models on self-generated trajectories. However, the on-policy nature of GRPO bounds the model to the reasoning skills it can already produce, restricting to learn more advanced capabilities. Prior works inject privileged reasoning traces from a stronger teacher policy to guide training, yet these traces are inherently out of distribution with respect to the student policy. We observe that this mismatch between on-policy and off-policy causes gradient clipping on semantically critical reasoning tokens, ultimately rewarding correct answers while leaving the reasoning that justifies them unlearned. Hence, we propose \textbf{Echo-GRPO}, a framework that lets the model reason in the words it speaks. Rather than imitating low-probability privileged traces from the teacher model, Echo-GRPO rewrites them into the student policy's own \textit{idiolect}, that is, its own characteristic vocabulary and expression patterns, while preserving their semantics via Dual-Reference Decoding. We instantiate this framework as \textbf{VideoEcho-R1} for video reasoning distillation, achieving consistent improvements across three multimodal LLM backbones and five benchmarks. Finally, we show that our idiolectal paraphrasing is a plug-in module that consistently improves both RL and supervised fine-tuning frameworks for reasoning distillation, demonstrating that policy-aligned supervision extends beyond GRPO.
Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-policy self-distillation (OPSD) and its variants have emerged as a promising paradigm, providing dense token-level supervision on student-generated rollouts, yet their objectives do not explicitly prioritize reasoning signals most critical to cross-lingual transfer. We characterize that target-language reasoning comprises the generation of both surface text and reasoning pivots, which are decisions that advance or redirect the reasoning process and shape subsequent inference. This motivates concentrating privileged distillation around such pivots. We therefore propose RP-OPSD, Reasoning-Pivot-guided On-Policy Self-Distillation, using the distributional shift between matched teacher views with and without an English reference solution as an operational proxy to guide privileged distillation and reference anchoring. Experiments on mathematical reasoning benchmarks covering 17 languages and multiple difficulty levels show that our method outperforms strong multilingual reasoning baselines and OPSD variants. Further analysis reveals that RP-OPSD concentrates privileged distillation on reasoning-control and problem-condistioned state-update tokens, while downweighting it for tokens that mainly support surface realization. Our code is available at https://github.com/NJUNLP/RP-OPSD.
Off-Context GRPO (OC-GRPO), a minimally modified variant of GRPO that uses guided rollouts but applies an importance-corrected objective to steer the update back toward the original unguided objective, avoiding the mismatch that destabilizes uncorrected guided training.
Priyank Agrawal, Ankur Samanta, S. Ghasemlou et al.· arXiv.org· 1 citation
Vision-Language-Action (VLA) models have become the dominant recipe for generalist manipulation, yet they are almost universally trained by behavior cloning: a policy imitates expert action chunks conditioned on a static image and a fixed instruction. A natural remedy is to inject explicit reasoning through textual chain-of-thought (CoT). We show, both empirically and analytically, that free-form textual CoT degrades low-level control: the reasoning it produces is ungrounded, its latency breaks closed-loop timing, and, crucially, the reasoning and action tokens are optimized against conflicting objectives so that the policy learns to narrate rather than to act. We argue that what a VLA needs is not the ability to generate language, but the ability to consume grounded language. To this end we introduce \textbf{\ourmethod{}}, a framework that endows a VLA with language competence through (i) in-context post-training, in which perceptual evidence is injected as structured context and the model is supervised only on actions, and (ii) an agentic tool-use interface, in which the policy queries open-vocabulary detectors, monocular depth, and a vision--language model to actively acquire task-relevant information. Rather than emitting a single templated caption, our data engine produces diverse, paraphrased, and evidence-conditioned spatial descriptions, so that the policy learns to interpret language it has never seen verbatim. Across the RoboCasa-GR1, SimplerEnv, and LIBERO simulation benchmarks, together with 8 real-world robot manipulation tasks, our method consistently achieves SOTA results in both performance and efficiency when compared with CoT-based approaches under matched configurations.
Jiaru Yang, Wen Huang, Jiale Zhang et al.· 0 citations
This work shows that reasoning traces are not a prerequisite: skills distilled from non-reasoning trajectories alone remain competitive with skills distilled from paired reasoning/non-reasoning corpora, with domain-dependent differences between the two sources.
Agamdeep Singh, Srishti Gautam, Priyanshu Gupta et al.· 0 citations
This work introduces a student reference KL loss and mask the advantages of special termination tokens to mitigate the problem of excessive generation length and frequent truncation, and improves on science benchmarks such as HLE and HiPhO, suggesting that OPD transfers reasoning capabilities that generalize beyond the mathematical training domain.
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards leads to limited guidance on intermediate reasoning processes. Existing approaches such as process reward modeling and on-policy distillation introduce additional constraints, such as reliance on a specialized reward model or assuming identical reasoning patterns between teacher and student. Nevertheless, we observe that once a reasoning process first goes wrong, evaluating the subsequent reasoning provides limited additional information, as it is already conditioned on an invalid prefix. Therefore, we propose Cliff, a reward shaping strategy that utilizes an off-the-shelf LLM as a teacher to identify the first mistake in each rollout. As a result, the rollout is naturally decomposed into two parts: a correct prefix and an incorrect suffix. Cliff then converts this signal into token-level advantages, assigning positive advantages for the correct prefix and negative feedback afterward. Experiments across 12 different scenarios demonstrate that Cliff consistently improves reasoning performance, outperforming on-policy distillation by 15% and standard GRPO by 7%, even with teachers of modest capability. Furthermore, we analyse the role of ``ground truth''in Cliff and investigate its training dynamics. These results establish Cliff as a simple, general and effective approach for improving RLVR with richer, fine-grained supervision.
Peixuan Han, Runnan Wang, Ketan Ramaneti et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
