arXiv Machine Learning June 25, 2026 By Michal Podstawski

Closed-Loop Graph Algorithm Execution with Small Language Models: Step Accuracy and Rollout Reliability

Read the original on arXiv Machine Learning →

arXiv:2606. 24980v1 Announce Type: new Abstract: Small language models offer an efficient alternative to large-scale systems, but their ability to execute structured algorithms over multiple dependent decisions remains poorly understood.

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

arXiv AI

2d ago

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.

By Ismail El Hamraoui, Sagar Jose, Nicolas Bureau, Robert Plana

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 29

Understanding Rollout Error in Graph World Models

arXiv:2606. 27780v1 Announce Type: new Abstract: World models are often used for planning by rolling learned dynamics forward.

By Xinyuan Song, Zekun Cai

agents benchmarks

arXiv AI

Jun 29

Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents

arXiv:2606. 27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms.

By Xinyuan Song, Zekun Cai

llms agents benchmarks safety

arXiv AI

Aug 11

PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling

arXiv:2608. 08700v1 Announce Type: new Abstract: Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents.

By Dongjie Xu, Julius, Hanchi Dong, Minghua Tang, Yuxuan Sun, Ziwei Nie, Zicheng Liu, Dujun Qing, Jiajie Xu

llms agents benchmarks safety

arXiv AI

Jul 1

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

arXiv:2606. 31270v1 Announce Type: cross Abstract: Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and versatility.

By Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy, Yuhui Zhang

llms agents fine-tuning multimodal benchmarks

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

Related stories

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

Understanding Rollout Error in Graph World Models

Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents

PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function Calling

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

Experience Memory Graph: One-Shot Error Correction for Agents