English
Related papers

Related papers: Polar: Agentic RL on Any Harness at Scale

200 papers

Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to…

Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application is stifled by low sample efficiency. Recent Human-in-the-Loop…

Robotics · Computer Science 2026-03-10 Haojun Chen , Zili Zou , Chengdong Ma , Yaoxiang Pu , Haotong Zhang , Yuanpei Chen , Yaodong Yang

Large language models have enabled agentic systems that reason, plan, and interact with tools and environments to accomplish complex tasks. As these agents operate over extended interaction horizons, their effectiveness increasingly depends…

Artificial Intelligence · Computer Science 2026-03-17 Yue Xu , Qian Chen , Zizhan Ma , Dongrui Liu , Wenxuan Wang , Xiting Wang , Li Xiong , Wenjie Wang

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective multi-turn and tool-integrated reasoning. While instructions…

Machine Learning · Computer Science 2026-02-03 Han Zhou , Xingchen Wan , Ivan Vulić , Anna Korhonen

Long-horizon language-model agents are dominated, in lines of code and in operational complexity, not by their underlying model but by the harness that wraps it: context compaction, tool caching, semantic memory, trajectory reuse,…

Machine Learning · Computer Science 2026-04-24 Biswa Sengupta , Jinhua Wang

Developing a reinforcement learning (RL) agent often involves identifying values for numerous parameters, covering the policy, reward function, environment, and agent-internal architecture. Since these parameters are interrelated in complex…

Machine Learning · Computer Science 2025-04-03 Francisco Erivaldo Fernandes Junior , Antti Oulasvirta

Progress in designing channel codes has been driven by human ingenuity and, fittingly, has been sporadic. Polar codes, developed on the foundation of Arikan's polarization kernel, represent the latest breakthrough in coding theory and have…

Information Theory · Computer Science 2024-06-06 S Ashwin Hebbar , Sravan Kumar Ankireddy , Hyeji Kim , Sewoong Oh , Pramod Viswanath

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed…

Artificial Intelligence · Computer Science 2026-03-31 Yoonho Lee , Roshen Nair , Qizheng Zhang , Kangwook Lee , Omar Khattab , Chelsea Finn

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and…

Machine Learning · Computer Science 2025-04-22 Hikaru Shindo , Quentin Delfosse , Devendra Singh Dhami , Kristian Kersting

Reinforcement learning (RL) has enabled the training of large language model (LLM) agents to interact with the environment and to solve multi-turn long-horizon tasks. However, the RL-trained agents often struggle in tasks that require…

Machine Learning · Computer Science 2026-03-10 Yulun Jiang , Liangze Jiang , Damien Teney , Michael Moor , Maria Brbic

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and…

Machine Learning · Computer Science 2024-11-06 Peiyuan Feng , Yichen He , Guanhua Huang , Yuan Lin , Hanchong Zhang , Yuchen Zhang , Hang Li

We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. ComputerRL features the API-GUI paradigm, which unifies programmatic API calls and direct GUI…

Artificial Intelligence · Computer Science 2025-10-22 Hanyu Lai , Xiao Liu , Yanxiao Zhao , Han Xu , Hanchen Zhang , Bohao Jing , Yanyu Ren , Shuntian Yao , Yuxiao Dong , Jie Tang

The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Moving beyond traditional qualitative reviews, this work presents a large-scale, data-driven…

Artificial Intelligence · Computer Science 2026-04-14 Lijing Luo , Yiben Luo , Alexey Gorbatovski , Sergey Kovalchuk , Xiaodan Liang

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit…

Cryptography and Security · Computer Science 2026-02-25 Yanna Jiang , Delong Li , Haiyu Deng , Baihe Ma , Xu Wang , Qin Wang , Guangsheng Yu

Large Language Models (LLMs) have emerged as one of the most significant technological advancements in artificial intelligence in recent years. Their ability to understand, generate, and reason with natural language has transformed how we…

Artificial Intelligence · Computer Science 2025-07-03 Yanfei Zhang

This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable…

Signal Processing · Electrical Eng. & Systems 2025-12-30 Hieu Le , Oguz Bedir , Mostafa Ibrahim , Jian Tao , Sabit Ekin

Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the…

Reproducibility problems that have long affected machine learning and reinforcement learning are now surfacing in agent research: papers compare systems by reported scores while leaving the rollout records behind those scores difficult to…

Artificial Intelligence · Computer Science 2026-05-13 Charlie Masters , Ziyuan Liu , Stefano V. Albrecht

Multi-Agent Reinforcement Learning (MARL) is central to robotic systems cooperating in dynamic environments. While prior work has focused on these collaborative settings, adversarial interactions are equally critical for real-world…

Machine Learning · Computer Science 2025-10-03 Isaac Peterson , Christopher Allred , Jacob Morrey , Mario Harper

The growing complexity and capacity demands for mobile networks necessitate innovative techniques for optimizing resource usage. Meanwhile, recent breakthroughs have brought Reinforcement Learning (RL) into the domain of continuous control…

Networking and Internet Architecture · Computer Science 2022-10-28 Vegard Edvardsen , Gard Spreemann , Jeriek Van den Abeele