arXiv:2602. 08222v2 Announce Type: replace Abstract: As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns.
Large language model (LLM) agents require post-training methods that can improve long-horizon decision making from environment feedback. However, existing agentic post-training pipelines often treat data curation as a fixed preprocessing step, focusing mainly on data augmentation while neglecting filtering, refinement, and adaptation to downstream failures.
arXiv:2607. 28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD).
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher.
The paper introduces Stable-MM-R1, a framework that stabilizes reinforcement learning for multimodal reasoning by addressing training instability and entropy collapse. It proposes Potential‑Aware Query Mining (PAQM) to filter data toward high‑potential samples and Hybrid Stratified Replay (HSR) to restructure batches using path entropy and reward stratification, reusing stability anchors and hard negatives. The method demonstrates superior performance on complex reasoning tasks compared to strong baselines.
Aligning large language models to human-centered objectives is difficult when targets are non-executable and context-dependent, limiting reliable verification and scalable supervision. Although synthe...
arXiv:2607. 20668v1 Announce Type: cross Abstract: TextGrad improves language-model systems by revising text from feedback.
arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm,...
arXiv:2608. 05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them.
SOD: Step-wise On-policy Distillation for Small Language Model Agents proposes a new framework that adaptively reweights distillation strength at each reasoning step based on step-level divergence. This approach mitigates cascading errors in tool-integrated reasoning by attenuating misleading teacher signals in high-divergence regions while preserving dense guidance where student and teacher align. Experiments on math, science, and code benchmarks show up to 20.86% improvement over the second-best baseline, with a 0.6B student scoring 26.13% on AIME 2025.
The paper reports that in on‑policy distillation for large language models, reasoning performance can be improved by supervising only a tiny fraction of generated tokens—sometimes just one or two tokens per reasoning trajectory, about 0.05% of all tokens. This sparse supervision consistently matches or exceeds full‑token training across nine teacher‑student setups on mathematical reasoning, and is also validated on coding reasoning, Llama models, and PPO‑based reinforcement learning with verifiable reward. The findings suggest that effective post‑training does not require token‑intensive supervision and may align more closely with natural learning processes that focus on critical reasoning steps.
arXiv:2608.23493v1 Announce Type: new Abstract: Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However,...
arXiv:2509. 02522v3 Announce Type: replace-cross Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming, however existing RLVR methods often suffer from sparse reward signals and unstable policy gradient updates inherent to RL-based approaches.