arXiv AI August 17, 2026 By Ismail El Hamraoui, Sagar Jose, Nicolas Bureau, Robert Plana

A Graph-Based Reinforcement Learning Framework for Structured Drift Diagnosis and Recovery in Autonomous LLM Agents

arXiv:2608. 14109v1 Announce Type: new Abstract: Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviation from the original task that can lead to irreversible side effects on external systems.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 16

Experience Memory Graph: One-Shot Error Correction for Agents

arXiv:2607. 13884v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations.

By Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng

llms agents benchmarks

arXiv AI

Jun 8

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

arXiv:2606. 07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks.

By Chuan Xiao, Zhengbo Jiao, Shaobo Wang, Wei Wang, Bing Zhao, Hu Wei, Linfeng Zhang, Lin Qu

llms agents safety

arXiv AI

1d ago

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

arXiv:2608. 16002v1 Announce Type: cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments.

By Zhengzhao Ma. Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

llms agents benchmarks safety

arXiv Machine Learning

Jun 8

Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes

arXiv:2606. 07127v1 Announce Type: new Abstract: Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed.

By Hikaru Shindo, Yu Deng, Teng Cao, Quentin Delfosse, Christopher Tauchmann, Jannis Bl\"uml, Gopika Sudhakaran, Kristian Kersting

llms agents nlp benchmarks

arXiv AI

Jun 9

ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

arXiv:2605. 16309v2 Announce Type: replace Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired.

By Safayat Bin Hakim, Keyan Guo, Wenkai Tan, Alvaro Velasquez, Shouhuai Xu, Houbing Herbert Song

llms agents benchmarks safety

arXiv AI

Jul 15

Tracing Agentic Failure from the Flow of Success

arXiv:2607. 12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.

By Samuel Yeh, Yiwen Zhu, Shaleen Deep, Sharon Li

llms agents diffusion

Related stories

Experience Memory Graph: One-Shot Error Correction for Agents

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes

ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

Tracing Agentic Failure from the Flow of Success