# LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories

arXiv: https://arxiv.org/abs/2608.15242 · HTML: https://mlsanity.com/paper/2608.15242/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 25 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 23 of 23)

- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [AgentRx: Diagnosing AI Agent Failures from Execution Trajectories](https://mlsanity.com/paper/2602.02475/) (2026)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [Analyzing Dataset Annotation Quality Management in the Wild](https://mlsanity.com/paper/2307.08153/) (2023)
- [Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis](https://mlsanity.com/paper/2509.13782/) (2025)
- [Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution](https://mlsanity.com/paper/2510.04886/) (2025)
- [Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2604.22708/) (2026)
- [The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break](https://mlsanity.com/paper/2604.11978/) (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)
- [From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2602.23701/) (2026)
- [Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference](https://mlsanity.com/paper/2509.08682/) (2025)
- [Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?](https://mlsanity.com/paper/2607.09996/) (2026)
- [CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems](https://mlsanity.com/paper/2509.24088/) (2025)
- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search](https://mlsanity.com/paper/2606.00765/) (2026)
- [TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems](https://mlsanity.com/paper/2605.26563/) (2026)
- [SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation](https://mlsanity.com/paper/2606.24626/) (2026)

## Built on by (most cited first, 2 of 2)

- [Detect Before You Attribute: Cascade Failure Attribution for Multi-Agent Systems](https://mlsanity.com/paper/2608.29646/) (2026)
- [Executable Prefix Values for Locating Agent Failures](https://mlsanity.com/paper/2610.17633/) (2026)

## Abstract (arXiv)

In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed across the history. Short histories offer limited tests of recovering error origins across substantial subsequent execution. We introduce LongRCA Bench: 1,140 complete failed trajectories from five sources, all human-annotated for responsible roles and earliest decisive root-cause steps. Reference roots precede completion by a median of 48 recorded steps; 28.4% of trajectories contain over 100 subsequent steps. With DeepSeek-V4-Flash on the full benchmark, the strongest of five evaluated baselines achieves 13.2% exact root-step accuracy. We propose Root-Cause Trajectory Attribution (RCTA), a training-free method that organizes original candidate records and explicit handoff instructions for attribution. Segment summaries and a trajectory outline guide candidate retrieval; available handoff records supply upstream instruction context for the final instruction-execution comparison. With the same backbone and scoring protocol, RCTA reaches 24.1% exact root-step accuracy and 51.1% responsible-role accuracy. LongRCA-Mini provides 200 fixed trajectories for lower-cost comparative screening. Even with RCTA, fewer than one quarter of reference roots are recovered exactly.