This work introduces ROSS (Relearning from Self-Generated Rollouts through Selective Supervision), which preserves the full historical trajectory as context while applying loss only to selected model-generated continuations.
Abstract
Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience is often treated as stale once the policy advances. Historical rollouts can remain compatible with a later policy while preserving behaviors that the policy no longer expresses reliably. However, they may also contain mistakes, abandoned attempts, and redundant actions that should not be imitated, motivating finer-grained selective supervision. We introduce ROSS (Relearning from Self-Generated Rollouts through Selective Supervision), which preserves the full historical trajectory as context while applying loss only to selected model-generated continuations. Across domain-specific reinforcement learning, multi-teacher on-policy distillation, and agentic reinforcement learning, ROSS consistently improves upstream checkpoints and outperforms baselines across mathematics, code generation, instruction following, and software engineering. On Qwen3.6-35B-A3B, ROSS improves the six-benchmark MOPD average from 58.40% to 62.20% and SWE-bench Verified from 64.20% to 68.40%. These results show that self-rollout training leaves behind reusable behavioral experience that can yield further gains through offline supervised fine-tuning (SFT), without additional policy rollouts.
This work introduces Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation, and introduces privileged disagreement correction to explicitly suppress locally overvalued actions.
Activation-Conditioned Self-Distillation (ACSD), which extracts a steering vector by contrasting activations of self-generated trajectories that reach verified correct answers within a generation budget with those of all remaining trajectories, achieves the highest mean accuracy over four mathematical benchmarks among...
On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its reliance on frequently refreshed student rollouts often incurs substantial generation cost. We introduce REVO, an off-policy distillation framework that improves rollout effici...
Experiments spanning mathematical reasoning, multi-domain STEM, code generation, and multi-turn agentic tasks show that RISE outperforms RLVR-only training and on-policy self-distillation across all settings.
Yang Li, Semih Yavuz, Shafiq Joty· 5 citations· ⚡1
Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across long interactions. However, our diagnostic analysis shows that agents often fail to act on relevant information already available in context, while final Pass/Fail outc...
Yu-Jia Luo, Zhi-Yi Lai, Zi-Qi Miao et al.· 0 citations
This work proposes self-instructing policy optimization (SIPO) with a contrastive self-teacher to provide dense credit, and demonstrates that SIPO outperforms both RLVR and OPSD baselines without an external teacher or additional generation.
Zhenrui Yue, Hui-Min Zeng, Yue-Qi Wang et al.· arXiv.org· 1 citation
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.