AdaptEvo is a framework that learns under imperfect supervision by combining confidence‑adaptive policy optimization (CA‑GRPO) with evolving decision knowledge and evaluation rubrics. Its training module balances outcome and process rewards based on reference confidence, while its evolution module extracts reusable knowledge from recurring failures and refines process rubrics to catch overlooked errors. On an industrial multimodal content‑moderation dataset, AdaptEvo with Qwen3.6‑35B‑A3B achieves 61.9% exact‑label accuracy and 72.2% binary decision accuracy on in‑period tests, outperforming GRPO by 7.5 and 3.7 percentage points, and maintains gains on out‑of‑period tests even as GRPO performance declines.
By AllSpark Team
arXiv:2610.02824v1 Announce Type: new
Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requireme...
By Yuxuan Fan, Jaehong Yoon
TextualRL is a gradient‑free reinforcement learning framework that updates the textual context guiding large language model agents without altering their parameters. It treats groups of rollouts from the same task as units of critique, contrasting successful and failed runs to generate context patches, and validates these patches using held‑out rewards. Experiments on six benchmarks show that TextualRL boosts test accuracy by 24.4 and 15.3 percentage points for GPT‑5.5 and Qwen3.8‑27B, respectively.
By Tianyu Huai, Jie Zhou, Bo Mao, Qin Chen, Liang He, Xipeng Qiu
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.
The paper proposes a two-stage adaptive training framework for GUI agents that addresses both where to learn and how far to roll out during training. It creates reusable intermediate checkpoints from expert trajectories and selects informative pivots using action disagreement to focus one-step reinforcement learning on uncertain decisions. The method then progressively expands policy responsibility through adaptive Local, Suffix, and Root training, enabling repeated training from intermediate states and reducing environment interaction by 56‑61% while improving task performance on MobileGym and CUA‑Gym‑Hub.
By Yuxiang Chai, Quyu Kong, Panrong Tong, Steven Hoi, Yue Wang
arXiv:2606. 03980v1 Announce Type: new Abstract: Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines.
By Tao Chen, Gangwei Jiang, Pengyu Cheng, Siyuan Huang, Yihao Liu, Jingwei Ni, Jiaqi Guo, Mengyu Zhou, Kai Tang, Junling Liu, Qinliang Su, Xiaoxi Jiang, Guanjun Jiang