The paper introduces FACA, a Feedback‑Aware Credit Assignment method that aligns each agent reaction with the preceding user‑to‑user segment, derives a locally normalized reaction advantage, and adds it to the terminal outcome advantage without requiring an extra critic or rollout. Compared to an outcome‑only Interactive GRPO baseline, FACA improves performance across nine domains by 5.91–10.22 percentage points on 8B and 14B models, with notable gains in Telecom. The approach demonstrates that next‑turn user reactions provide actionable local credit for enhancing multi‑turn user‑interacting agents.
The paper tackles sample efficiency in image-based reinforcement learning by combining novelty and surprise signals to prioritize experiences. It proposes Novelty and Surprise Prioritized Experience Replay (NSPER) and an extended version, NSPER+R, which also uses these signals as intrinsic rewards. Experiments on DeepMind Control Suite tasks demonstrate that both methods accelerate training and improve convergence compared to existing techniques.
arXiv:2608. 15510v1 Announce Type: new Abstract: Chart-to-code generation requires a model to read the fine-grained visual details of a chart and write executable code that reproduces it.
By Qinghao Fu, Yarong Wang, Shunlei Ning, Yilin Wang, Shunwen Bai, Xinda Wang, Jiaotuan Wang, Yinan Nie, Wei Zhou
arXiv:2608. 15680v1 Announce Type: cross Abstract: Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states.
By Yijie Xu, Haopeng Jin, Run Zhou, Shengbang Liu, Sixiang Chen, Hongyang Cheng, Sicheng Hu, Peterson Co, Jinwen Luo, Huajie Tan, Shanghang Zhang
arXiv:2608. 15041v1 Announce Type: new Abstract: Coordinating multiple interacting units in complex engineering systems is challenging when system interactions are difficult to model, operational information is heterogeneous, and low-level actions must satisfy strict constraints.
By Changhong He, Jinda Gao, Xinkuan Liu, Le Zhang, Xizi Luo, Yu Mei
arXiv:2608. 15949v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and natural dialogue.
By Cedar Site Bai, Duanshun Li, Zhenyu Liao, Sheikh Sarwar, Huiyuan Chen, Yuan Chen, Changhe Yuan, Haiyang Zhang, Qilin Qi
arXiv:2608. 14635v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments.
By Jiecheng Zhou, Qinghao Hu, Peng Sun, Xingcheng Zhang, Weiming Zhang
arXiv:2608. 15660v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge.
By Chenwang Liu, Yijun Liu, Chang Liu, Xu Zhang, Pengchao Han
arXiv:2608. 14851v1 Announce Type: new Abstract: Learning and skill mastery require extensive and deliberate practice.
By Allen Nie, Anirudhan Badrinath, Nicholas Tomlin, Timothy Dai, Carissa Yip, Rose E Wang, Emma Brunskill, Chris Piech
arXiv:2605. 02909v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs).
By Kazuki Egashira, Mark Vero, Jasper Dekoninck, Florian E. Dorner, Robin Staab, Martin Vechev
arXiv:2608. 00270v2 Announce Type: replace Abstract: Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP).
By David Aguado, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar
arXiv:2509. 16586v2 Announce Type: replace Abstract: Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the generative model.
By Yukuan Wei, Xudong Li, Lin F. Yang
arXiv:2603. 24575v2 Announce Type: replace-cross Abstract: Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability.
By Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Zhongzheng Ren, Daniel S Weld, Ranjay Krishna
arXiv:2608. 16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences.
By Ondrej Bajgar, Peter Tisnikar, Alessandro Abate, Konstantinos Gatsis, Maike Osborne
arXiv:2608. 16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts.
By Junqi Liu, Yufan He, Yexiao He, Pengfei Guo, Dong Yang, Andriy Myronenko, Can Zhao, Hanrong Ye, Tianhao Qi, Yuyin Zhou, Daguang Xu, Yucheng Tang
arXiv:2602. 09761v2 Announce Type: replace-cross Abstract: In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments.
By Matteo Pannacci, Andrea Fanti, Elena Umili, Roberto Capobianco
arXiv:2510. 00358v2 Announce Type: replace-cross Abstract: Soft snake robots offer remarkable flexibility and adaptability in complex environments, yet their control remains challenging due to highly nonlinear dynamics.
By Linjin He, Xinda Qi, Dong Chen, Zhaojian Li, Xiaobo Tan
arXiv:2506. 15700v2 Announce Type: replace-cross Abstract: Control contraction metrics (CCMs)-defined by Riemannian metrics under which a closed-loop system is incrementally exponentially stable-offer a constructive framework for synthesizing contracting policies in nonlinear path-tracking problems.
By Minjae Cho, Hiroyasu Tsukamoto, Huy T. Tran
The paper proposes a principled communication strategy for multi‑agent reinforcement learning that gates messages based on the KL divergence between agents’ belief distributions over a latent world state. Each agent maintains a softmax belief derived from its LSTM hidden state and only communicates when disagreement exceeds a fixed threshold. Experiments on Predator‑Prey and MPE simple_spread show that this KL‑belief gating can match or surpass existing methods, improving performance and reducing variance in certain settings.
By Teoman Kaman
arXiv:2506. 01584v2 Announce Type: replace-cross Abstract: Developing machine learning (ML) systems for real-world deployment requires navigating context-dependent trade-offs among accuracy, fairness, stability, and other objectives.
By Denys Herasymuk, Anastasiia Mozghova, Nazar Protsiv, Vladyslav Sydorak, Julia Stoyanovich