The paper presents a deep reinforcement learning framework that explicitly incorporates uncertainty quantification for risk and anomaly identification in distribution network operation. It combines distributional and Bayesian DRL to separate total uncertainty into aleatoric (inherent risk) and epistemic (out‑of‑distribution anomalies) components. The epistemic estimates guide exploration during training and enable anomaly detection with fallback control during deployment, while aleatoric estimates assess intrinsic operational risk.
By Ziqi Zhang
The paper reviews how Large Language Models (LLMs) are being adapted for medical reasoning, moving beyond single-step answers to systems that can systematically, transparently, and verifiably reason. It introduces a taxonomy of enhancement techniques, split into training-time methods such as supervised fine‑tuning and reinforcement learning, and test-time methods like prompt engineering and multi‑agent systems. The review examines their application across text, image, and code modalities in key clinical areas—diagnosis, education, and treatment planning—and tracks the shift in evaluation benchmarks from simple accuracy to more nuanced assessments of reasoning quality and visual interpretability.
By Zizhan Ma, Wenxuan Wang, Meidan Ding, Shiyi Zheng, Shengyuan Liu, Jie Liu, Jiaming Ji, Linlin Shen, Yixuan Yuan, Wenting Chen
The paper introduces Test Cases Scaling (TCS), a two‑stage reinforcement learning framework that automatically generates sound and discriminative test cases for code large language models (LLMs). Stage 1 trains a test generator to produce tests aligned with a reference solution, while Stage 2 refines the generator to produce counterexample tests that target the solver’s current failure modes. Experiments on TACO and LiveCodeBench show that TCS improves pass@1 and inference‑time answer selection, and the learned test generator can also effectively rank outputs from other LLMs.
By Jiacheng Xu, Wentao Zhang, Zhiyi Lyu, Fuxiang Zhang, Chaojie Wang, Yang Liu, Bo An
WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.
By Yibin Wang, Zehan Wang, Junshu Tang, Zhimin Li, Yujie Zhou, Jiazi Bu, Pengyang Ling, Feng Han, Zhixiong Zhang, Long Xing, Shengyuan Ding, Ziang Li, Cheng Jin, Yuhang Zang, Jiaqi Wang, Tianyu Pang
The paper introduces F-GRPO, a method that addresses the issue of reinforcement learning policies overfitting to common trajectories while neglecting rare correct ones. By deriving the probability of prompt‑local tail‑miss events and proposing a difficulty‑aware scaling coefficient inspired by Focal loss, the authors show that down‑weighting high‑success sampled groups can improve performance. Experiments on categorical simulations, Maze, and large language models (Qwen2.5‑7B) demonstrate that F‑GRPO raises average math pass rates and out‑of‑distribution performance without increasing group size or computational cost.
By Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daria Korotyshova, Daniil Gavrilov
The paper proposes a deployment‑focused framework for deadline‑constrained network control, introducing the Effective Congestion (EC) metric family and Uniform Path Grouping (UPG) heuristic to better capture traffic urgency and balance load. It integrates these with a Multi‑Agent Deep Reinforcement Learning architecture (MADRL EC (p*)) that combines a distributed scheduler and a centralized RL router. A unified training objective merges live‑reward, pre‑collected‑reward, and policy‑imitation terms, leading to the Model‑Guided Annealed Reinforcement Learning (MGA‑RL) protocol built on DDPG, which generalizes offline‑to‑online learning for demonstration‑driven training.
By Vincenzo Norman Vitale, Mohammad Solki, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca
ToPO (Token-Oriented Preference Optimization) is a method for attention-based latent diffusion models that constructs a per‑minibatch, detached, separable spatial‑temporal route using branchwise squared‑residual contrast from a frozen reference denoiser. It employs preferred‑branch cross‑attention with content tokens to modulate spatial factors and adds an auxiliary pixel‑midpoint ordering term, all without local labels or a learned reward model. In experiments with shared update schedules, ToPO outperforms Diffusion‑DPO on five SD‑1.5 metrics and on HPSv2, ImageReward, and CLIP for SDXL, and achieves higher raw win shares in a blind SDXL A/B study.
By Juntao Xu, Shihong Li, Hoi Fan Au, Ning Zhu
The paper investigates how on-policy distillation (OPD) and reinforcement learning with verifiable rewards (RLVR) can be combined for post‑training reasoning in large language models. It shows that a two‑stage approach—first applying OPD, then RL—outperforms single‑signal methods and other joint baselines on logic and math reasoning benchmarks. The authors explain this advantage through pass@k analysis, learning dynamics, and parameter updates, concluding that OPD expands solution coverage while RL sharpens performance within that support, and that the OPD validation score is the key trigger for switching to RL.
By Boyan Li, Bingsen Chen, Chenghao Yang, Ping Nie, Chen Zhao, Xi Ye
StrixAE is an intelligent audio enhancement agent that uses a multimodal large language model to coordinate multiple enhancement and personalization models. It is trained in two stages: first, chain‑of‑thought supervised fine‑tuning on AcoustBench, and second, Audio Perception Reinforcement Learning that optimizes format validity, structural coherence, and perceptual quality. The approach yields state‑of‑the‑art performance and strong generalization on real‑world test datasets, outperforming many existing open‑source and proprietary solutions.
By Chenglin Wu, Junjie Wu, Jinhang Chen, Mingyang Chen, Zixu Lin, Jiabian Chen, Xinghao Ding, Xiaotong Tu
Group Relative Policy Optimization (GRPO) assigns a magnitude to each rollout based on within‑group reward statistics, rewarding rollouts that reach the correct answer through reasoning. However, the same magnitude can be high for rollouts that reach the answer by guessing, creating a spurious advantage that misleads the policy toward guess‑like behaviors. The paper identifies three scenarios where this occurs—bounded‑answer tasks, open‑answer sets with bounded sub‑cases, and search agents with many paths to the same answer—and proposes SIGNBALANCE, a composition‑free magnitude that preserves the verifier sign, uses a global scale, and restores zero‑mean balance via stop‑gradient per‑class rescaling, matching GRPO on open‑answer math and improving on bounded‑answer math and search agents.
By Jiamian Wang, Samyadeep Basu, Koustava Goswami, Tong Yu, Zhiqiang Tao
RL-ADA introduces a co‑evolutionary training framework that replaces costly human annotations with world‑feedback rewards derived from interaction outcomes. In this system, a large Customer Support Agent and an Adversarial Customer Agent train together, guided by an automated judge that rewards successful resolution and realistic intent‑concealing utterances, respectively. Applied to a banking support proof of concept, the method eliminates routing errors and doubles the end‑to‑end PASS rate over five cycles, while also revealing a new adversarial strategy called Contextual Camouflage.
By Ram Narayanan, Harshit Rajgarhia, Abhishek Mukherji
The paper presents a framework that uses saliency maps to create hierarchical attention profiles, tracking how deep reinforcement learning agents allocate attention over time. By comparing these attention trajectories across different conditions and linking them to behavioral metrics, the study reveals algorithm‑specific biases, unintended reward‑driven strategies, and overfitting to redundant sensory inputs. Experiments on Atari 2600 games, custom Pong environments, and biomechanical visuomotor simulations demonstrate that these attention patterns correspond to measurable behavioral differences, establishing attention trajectories as a diagnostic tool beyond traditional performance metrics.
By Charlotte Beylier, Hannah Selder, Arthur Fleig, Simon M. Hofmann, Nico Scherf
The paper investigates whether the text of chain‑of‑thought reasoning steps actually reflects their true importance for a model’s final answer. By defining step importance as the advantage in expected reward when a step is included, the authors use Monte Carlo rollouts to estimate ground truth and then test whether large language model judges can identify high‑advantage steps. They find that capable LLMs can beat a prevalence baseline but still fall far short of a noise ceiling, and that fine‑tuning a step‑level critic improves detection for incorrect responses but remains distant from the ceiling for correct ones, indicating that step importance is only partially recoverable from the reasoning trace text.
By Kevin Du, Alexander Hoyle, Laura Ruis, Acyr Locatelli
The paper introduces a formal framework that uses symmetries in data to keep causal mechanisms invariant, providing a simple and general mathematical language for causal reasoning. It outlines how to describe models and queries, and presents strategies for rigorously identifying causal effects from data within this framework. The approach reproduces known results for IID data and extends causal analysis to non‑IID settings, complex queries beyond do‑ or soft‑interventions, and incorporates missing data, transfer, and robustness considerations.
By Martin Rabel, Jakob Runge
RECAST is a new framework that generates datasets with far more constraints per example than existing benchmarks, aiming to push large language models (LLMs) to better follow complex instructions. The authors built RECAST-30K, a 30,000‑instance dataset covering 19 constraint types extracted from real prompt‑response pairs, and showed that fine‑tuning on it improves LLMs’ ability to handle complex tasks without harming general performance. RECAST also provides rule‑based and LLM‑based validators for automatic constraint verification, enabling reward‑based reinforcement learning to further enhance model performance on challenging tasks.
By Zhengkang Guo, Wenhao Liu, Mingchen Xie, Jingwen Xu, Zisu Huang, Muzhao Tian, Jianhan Xu, Yuanzhe Shen, Qi Qian, Muling Wu, Xiaohua Wang, Changze Lv, He-Da Wang, Hu Yao, Xiaoqing Zheng, Xuanjing Huang
The paper investigates the problem of over‑editing by large language models when repairing code, showing that even state‑of‑the‑art models like GPT‑5.5 frequently rewrite more code than necessary. Using a benchmark of 400 BigCodeBench problems with controlled AST corruptions, the authors quantify excess edits and demonstrate that a simple preservation instruction can reduce unnecessary changes and improve pass rates. They further explore training strategies, finding that reinforcement learning yields the best balance between edit fidelity and performance retention, highlighting edit fidelity as a distinct, measurable dimension of code‑repair quality.
By Tongyao Zhu, Wei Hern Lim, Min-Yen Kan
Gaokerena is a family of compact Persian medical language models designed for consumer‑grade hardware. The first variant, Gaokerena‑V, was trained on a 90‑million‑token Persian medical corpus and 20,000 physician Q&A pairs, raising a translated medical MMLU benchmark score from 46.28% to 49.31%. A second variant, Gaokerena‑R, adds a Chain‑of‑Thought approach and two Reinforcement Learning with AI Feedback frameworks, achieving a higher benchmark score of 52.98% while also providing uncertainty estimates based on internal hidden states.
By Mehrdad Ghassabi, Hamidreza Baradaran Kashani, Pedram Rostami, Sadra Hakim, Zahra Kazemi, Amirhossein Poursina, Milad Tavakoli, Audrina Ebrahimi
DRACO introduces a method for fine‑grained credit assignment in long‑horizon reinforcement learning tasks that lack verifiable rewards. It dynamically generates multi‑criteria rubrics during training, scores them once per trajectory, and redistributes the resulting judgment over the steps responsible for each rubric to produce differentiated per‑step advantages. Experiments on AppWorld and Tau‑Bench show significant performance gains over baseline models and other rubric‑based approaches, even without using any verifiers.
By Shubham Gandhi, Saurabh Goyal, Kiran Kate, Yara Rizk
The paper introduces Imagine-then-Plan (ITP), a framework that lets agents learn by interacting with a learned world model to generate multi-step imagined trajectories. ITP features an adaptive lookahead mechanism that balances ultimate goals with task progress, producing richer signals about future outcomes. Experiments on various benchmarks show that ITP outperforms existing baselines, and analyses suggest the adaptive lookahead improves reasoning for complex tasks.
By Youwei Liu, Jian Wang, Hanlin Wang, Beichen Guo, Wenjie Li
The paper investigates model‑free robust Q‑learning with χ² uncertainty sets and linear function approximation, using data from a single trajectory of an unknown nominal MDP. It introduces a variational reformulation of the robust Bellman target and a blockwise frozen‑target scheme to overcome estimation and non‑contractivity challenges, and proves a finite‑time error bound for every discount factor γ in (0,1). A neural‑network experiment demonstrates the practical use of the variational target in a continuous‑state nonlinear‑control task.
By Saptarshi Mandal, Yashaswini Murthy, R. Srikant