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
CAST is a critique‑aware training framework that transforms sparse task outcomes into action‑level supervision for both critique learning and policy optimization. By analyzing agent trajectories, CAST synthesizes structured rationales that explain action validity under partial observability, enabling the creation of richer training data. Fine‑tuned Qwen3‑family models trained with CAST show significant reliability gains, outperforming GPT‑OSS‑120B by over 10% on Retail tasks and improving Telehealth performance by 9% in an out‑of‑domain setting.
By Amir Saeidi, Zehua Zhang, Rishitosh Singh, Naman Ahuja, Vivek Gupta, Ali Payani, Gaowen Liu, Jayanth Srinivasa, Chitta Baral
arXiv:2606. 08480v1 Announce Type: cross Abstract: Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement.
By Kewei Xu, Junbo Qi, Yanyan Zou, Pengfei Zhang, Xingzhi Yao, Shengjie Li
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
By Kunlun Zhu, Xuyan Ye, Yibo Li, Cheng Qian, Beibin Li, Heng Ji
arXiv:2606. 01619v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) enables LLM agents to improve continuously from environment rewards, yet the resulting policies do not systematically accumulate reusable strategies that generalize across tasks.
By Zelin He, Haotian Lin, Boran Han, Wei Zhu, Haoyang Fang, Bernie Wang, Xuan Zhu, Runze Li, Matthew Reimherr
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
By Ye Chen, Weining Zhang
arXiv:2608.30005v1 Announce Type: new
Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific c...
By Fengyu Xie, Yilun Zhao, Bingsen Chen, Arman Cohan, Chen Zhao