arXiv AI August 26, 2026 By Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed, Zekun Wu, Kleyton Da Costa, Ilham Wicaksono, Adriano Koshiyama

Automata from Agent Traces: Failure and Next-Step Prediction

Read the original on arXiv AI →

The paper introduces a method to transform entire trace corpora of LLM-based agents into compact finite-state machines (FSMs) that capture shared behavioral structure. These FSMs, comprising 7–43 states, achieve near-perfect replay of held‑out data and enable accurate next‑step prediction and failure detection across twelve public datasets. The approach offers a model‑agnostic structural tool for safety auditing and runtime monitoring of agent behavior.

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 Machine Learning

Jun 10

From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents

arXiv:2606. 09863v1 Announce Type: new Abstract: LLM agents can fail silently by asserting task completion when the environment state shows otherwise.

By Laksh Advani

llms agents benchmarks

arXiv AI

Jun 2

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

arXiv:2606. 01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before producing an answer.

By Xianyou Li, Weiran Yan, Yichao Wu, Penghao Liang, Mengwei Yuan, Jianan Liu, Jing Yang

llms agents

arXiv AI

Jul 14

StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure

arXiv:2607. 11388v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use.

By Wenyi Wu, Sibo Zhu, Kun Zhou, Aayush Salvi, Zixuan Song, Biwei Huang

llms agents multimodal

arXiv Machine Learning

Jul 21

Self-Evolving Just-In-Time Memory for Proactive Embodied Safety

arXiv:2607. 16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions.

By Bingrui Sima, Lizhong Wang, Xiaoya Lu, Kun He, Xiao Yang

llms agents robotics multimodal safety

Hugging Face Trending Papers

Aug 4

Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks

Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.

agents

arXiv AI

Jul 8

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.

By Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Xuan Wang, Hao Sun

llms agents

One email a morning, machine-written

Related stories

From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents

Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability

StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure

Self-Evolving Just-In-Time Memory for Proactive Embodied Safety

Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks

Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade