arXiv AI August 18, 2026 By Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge, Ashmita Kapoor, Tanya Dixit

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

arXiv:2608. 15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve.

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 AI.

arXiv AI

Jun 30

Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem

arXiv:2606. 29116v1 Announce Type: new Abstract: Large Language Models (LLMs) are rapidly being adopted in low-code and no-code automation platforms, where non-expert users design workflows that combine natural language understanding with external services and APIs.

By Yutian Tang, Yuming Zhou, Huaming Chen

llms agents safety

arXiv AI

Jul 21

AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows

arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.

By Tejas Singh Anand, Yuet Ying Christina Wang, Wanting Jiang, Steve Masson, Tian Zheng, Bingjie Zhou

llms agents safety

arXiv AI

Jul 7

AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents

arXiv:2607. 02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges.

By La\"ila Elkoussy (LRE, EPITA), Julien Perez (LRE)

llms agents fine-tuning benchmarks safety

arXiv Machine Learning

Jun 16

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

arXiv:2606. 16000v1 Announce Type: cross Abstract: We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents.

By Aleksandr Tsymbalov, Danis Zaripov, Artem Epifanov, Anastasya Palienko

llms agents safety

arXiv AI

Aug 7

Agentic Software Issue Resolution with Large Language Models: A Survey

arXiv:2512. 22256v2 Announce Type: replace-cross Abstract: Software issue resolution aims to address real-world issues in software repositories based on natural language descriptions provided by users, and represents a key aspect of software maintenance.

By Zhonghao Jiang, David Lo, Zhongxin Liu

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 16

Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework

arXiv:2607. 13091v1 Announce Type: cross Abstract: LLM-based coding agents repeat the same classes of mistakes across sessions because they lack a mechanism to retain corrections from human review feedback.

By Aditya Aggarwal, Nahid Farhady Ghalaty

llms agents benchmarks

One email a morning, machine-written

Related stories

Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem

AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows

AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

Agentic Software Issue Resolution with Large Language Models: A Survey

Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework