arXiv Machine Learning August 19, 2026 By Ram Rachum, Yotam Amitai, B\'alint Gyevn\'ar, Reuth Mirsky, Cameron Allen

Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents

Read the original on arXiv Machine Learning →

The paper proposes EvalXRL, a benchmark that evaluates explainable reinforcement learning (XRL) methods by measuring how well their explanations help a large language model coding agent diagnose and fix bugs in RL agents. Unlike current metrics that focus on faithfulness or human ratings, EvalXRL uses a closed‑loop, scientific‑method style interaction where the coding agent repeatedly invokes XRL methods, refines hypotheses, and repairs the agent, scoring each method by the resulting RL reward. This approach enables a head‑to‑head comparison of multiple XRL techniques in realistic debugging scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 25

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

arXiv:2606. 26027v1 Announce Type: cross Abstract: Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities.

By Yupu Hao, Zhuoran Jin, Huanxuan Liao, Kang Liu, Jun Zhao

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 28

Evaluating Fuzz Testing for Reinforcement Learning Agents

arXiv:2607. 24577v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences.

By Zhibin Kang, Hanmo You, Dong Wang, Haiming Zheng, Junjie Chen

agents reinforcement-learning robotics efficiency benchmarks safety

arXiv AI

Jun 2

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.

By Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen, Yiju Guo, Shenzhi Yang, Wenkai Yang, Shuqi Ye, Jingwen Chen, Haotian Chen, Xin Cong, Yankai Lin

llms agents benchmarks

arXiv AI

Jun 2

From Features to Actions: Explainability in Traditional and Agentic AI Systems

arXiv:2602. 06841v4 Announce Type: replace Abstract: Over the last decade, Explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure.

By Sindhuja Chaduvula, Jessee Ho, Kina Kim, Aravind Narayanan, Ahmed Y. Radwan, Mahshid Alinoori, Muskan Garg, Dhanesh Ramachandram, Shaina Raza

llms agents

arXiv AI

Jun 3

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

arXiv:2512. 18552v3 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.

By Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel Synnaeve, Daniel Fried, Lingming Zhang, Sida Wang

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 15

Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL

arXiv:2606. 14211v1 Announce Type: new Abstract: LLMs are increasingly deployed as agents that interact with external environments and observe feedback such as execution results, error messages, and tool outputs.

By Yinglun Zhu

llms agents reinforcement-learning benchmarks data-engineering

One email a morning, machine-written

Related stories

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Evaluating Fuzz Testing for Reinforcement Learning Agents

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

From Features to Actions: Explainability in Traditional and Agentic AI Systems

Toward Training Superintelligent Software Agents through Self-Play SWE-RL

Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL