English
Related papers

Related papers: Efficient Agentic Reinforcement Learning with On-P…

200 papers

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Computation and Language · Computer Science 2025-10-21 Yushi Yang , Shreyansh Padarha , Andrew Lee , Adam Mahdi

Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration…

Sound · Computer Science 2026-02-17 Siqian Tong , Xuan Li , Yiwei Wang , Baolong Bi , Yujun Cai , Shenghua Liu , Yuchen He , Chengpeng Hao

Action advising endeavors to leverage supplementary guidance from expert teachers to alleviate the issue of sampling inefficiency in Deep Reinforcement Learning (DRL). Previous agent-specific action advising methods are hindered by…

Artificial Intelligence · Computer Science 2023-11-29 Yaoquan Wei , Shunyu Liu , Jie Song , Tongya Zheng , Kaixuan Chen , Yong Wang , Mingli Song

Many state-of-the-art adversarial training methods for deep learning leverage upper bounds of the adversarial loss to provide security guarantees against adversarial attacks. Yet, these methods rely on convex relaxations to propagate lower…

Machine Learning · Computer Science 2023-04-07 Dimitris Bertsimas , Xavier Boix , Kimberly Villalobos Carballo , Dick den Hertog

Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-checkable online rollouts. We propose COVERT, a two-stage…

Artificial Intelligence · Computer Science 2026-04-14 Siyuan Xu , Shiyang Li , Xin Liu , Tianyi Liu , Yixiao Li , Zhan Shi , Zixuan Zhang , Zilong Wang , Qingyu Yin , Jianshu Chen , Tuo Zhao , Bing Yin

In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest…

Machine Learning · Computer Science 2019-10-25 Heejin Jeong , Brent Schlotfeldt , Hamed Hassani , Manfred Morari , Daniel D. Lee , George J. Pappas

In this paper, we introduce an alternative approach to enhancing Multi-Agent Reinforcement Learning (MARL) through the integration of domain knowledge and attention-based policy mechanisms. Our methodology focuses on the incorporation of…

Machine Learning · Computer Science 2025-04-04 Andre R Kuroswiski , Annie S Wu , Angelo Passaro

Search-augmented reasoning agents interleave multi-step reasoning with external information retrieval, but uncontrolled retrieval often leads to redundant evidence, context saturation, and unstable learning. Existing approaches rely on…

Computation and Language · Computer Science 2026-02-03 Siheng Xiong , Oguzhan Gungordu , Blair Johnson , James C. Kerce , Faramarz Fekri

While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…

Software Engineering · Computer Science 2026-05-20 Yuxiang Wei , Zhiqing Sun , Emily McMilin , Jonas Gehring , David Zhang , Gabriel Synnaeve , Daniel Fried , Lingming Zhang , Sida Wang

Game theory provides the gold standard for analyzing adversarial engagements, offering strong optimality guarantees. However, these guarantees often become brittle when assumptions such as perfect information are violated. Reinforcement…

Machine Learning · Computer Science 2026-03-18 Goutam Das , Michael Dorothy , Kyle Volle , Daigo Shishika

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…

Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds…

Machine Learning · Computer Science 2025-12-09 Chris Tava

Advancements in reinforcement learning (RL) have inspired new directions in intelligent automation of network defense. However, many of these advancements have either outpaced their application to network security or have not considered the…

Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…

Machine Learning · Computer Science 2022-08-09 Archit Sharma , Kelvin Xu , Nikhil Sardana , Abhishek Gupta , Karol Hausman , Sergey Levine , Chelsea Finn

Capturing and simulating intelligent adaptive behaviours within spatially explicit individual-based models remains an ongoing challenge for researchers. While an ever-increasing abundance of real-world behavioural data are collected, few…

Multiagent Systems · Computer Science 2022-01-05 Sedar Olmez , Dan Birks , Alison Heppenstall

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…

Computation and Language · Computer Science 2026-01-16 Zihan Lin , Xiaohan Wang , Hexiong Yang , Jiajun Chai , Jie Cao , Guojun Yin , Wei Lin , Ran He

We propose a novel Reinforcement Learning (RL) method for optimizing quantum circuits using graph-theoretic simplification rules of ZX-diagrams. The agent, trained using the Proximal Policy Optimization (PPO) algorithm, employs Graph Neural…

Quantum Physics · Physics 2025-06-04 Jordi Riu , Jan Nogué , Gerard Vilaplana , Artur Garcia-Saez , Marta P. Estarellas

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation…

Machine Learning · Computer Science 2024-12-17 Juntao Dai , Yaodong Yang , Qian Zheng , Gang Pan

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…

Computation and Language · Computer Science 2026-05-25 Ranxu zhang , zeyang li , Jiacheng Huang , Rui Zhang , Xiaozhou Xu , sun zhe , Yanyong Zhang , Chao Wang

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…