# Structural Baselines Matter for Agent Failure Detection and Attribution

arXiv: https://arxiv.org/abs/2610.16661 · HTML: https://mlsanity.com/paper/2610.16661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Placed in

- LLM agents and tool use

## Builds on (most cited first, 17 of 17)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection](https://mlsanity.com/paper/2101.03778/) (2021)
- [Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2604.22708/) (2026)
- [Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation](https://mlsanity.com/paper/2603.25001/) (2026)
- [RAFFLES: Reasoning-based Attribution of Faults for LLM Systems](https://mlsanity.com/paper/2509.06822/) (2025)
- [Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?](https://mlsanity.com/paper/2607.09996/) (2026)
- [TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents](https://mlsanity.com/paper/2602.06443/) (2026)
- [From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents](https://mlsanity.com/paper/2606.09863/) (2026)
- [LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations](https://mlsanity.com/paper/2602.09924/) (2026)
- [Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI](https://mlsanity.com/paper/2601.00516/) (2026)

## Abstract (arXiv)

An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this, one deciding whether a run failed and the other naming the step where failure became unavoidable. Much of the reported performance on both tasks comes from regularities that need no model. Failing runs are longer, and the step labelled decisive is usually the last. A rule that always names the last step is correct 67% to 96% of the time here, without reading the run at all. That ceiling reflects how the labels were written, not how agents break. On failures whose decisive step replay can confirm, it falls to near chance. Reporting gain over that rule therefore changes what a score means. Under that correction, methods tested here gain nothing on give-up failures, while several published systems keep a clear advantage on other splits. For detection, the agent's internal states beat transcript length and text similarity on the agent benchmark, and hold up where the text baseline does not. Precision stays low when failures are rare, so such a monitor should rank runs for review, not replace it.