RAFFLES: Reasoning-based Attribution of Faults for LLM Systems

• URL: http://arxiv.org/abs/2509.06822v1
• Date: Mon, 08 Sep 2025 15:57:14 GMT
• Title: RAFFLES: Reasoning-based Attribution of Faults for LLM Systems
• Authors: Chenyang Zhu, Spencer Hong, Jingyu Wu, Kushal Chawla, Charlotte Tang, Youbing Yin, Nathan Wolfe, Erin Babinsky, Daben Liu,
• Abstract summary: RAFFLES is an evaluation architecture that incorporates reasoning and iterative refinement.<n>RAFFLES operates as an iterative, multi-component pipeline, using a central Judge to systematically investigate faults.<n>Results demonstrate a key step towards introducing automated fault detection for autonomous systems.
• Score: 4.950398945013938
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We have reached a critical roadblock in the development and enhancement of long-horizon, multi-component LLM agentic systems: it is incredibly tricky to identify where these systems break down and why. Evaluation capabilities that currently exist today (e.g., single pass LLM-as-a-judge) are limited in that they often focus on individual metrics or capabilities, end-to-end outcomes, and are narrowly grounded on the preferences of humans. We argue that to match the agentic capabilities, evaluation frameworks must also be able to reason, probe, iterate, and understand the complex logic passing through these systems over long horizons. In this paper, we present RAFFLES - an evaluation architecture that incorporates reasoning and iterative refinement. Specifically, RAFFLES operates as an iterative, multi-component pipeline, using a central Judge to systematically investigate faults and a set of specialized Evaluators to assess not only the system's components but also the quality of the reasoning by the Judge itself, thereby building a history of hypotheses. We tested RAFFLES against several baselines on the Who&When dataset, a benchmark designed to diagnose the "who" (agent) and "when" (step) of a system's failure. RAFFLES outperforms these baselines, achieving an agent-step fault pair accuracy of over 43% on the Algorithmically-Generated dataset (a substantial increase from the previously published best of 16.6%) and over 20% on the Hand-Crafted dataset (surpassing the previously published best of 8.8%). These results demonstrate a key step towards introducing automated fault detection for autonomous systems over labor-intensive manual human review.

Related papers

• Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis [5.532586951580959]
  We present a focused empirical evaluation that isolates an LLM's reasoning behavior.<n>We produce a labeled taxonomy of 16 common RCA reasoning failures and use an LLM-as-a-Judge for annotation.
  arXiv  Detail & Related papers  (2026-01-29T18:23:26Z)
• Insider Knowledge: How Much Can RAG Systems Gain from Evaluation Secrets? [24.068226474653617]
  Nugget-based approaches in particular are embedded not only in evaluation frameworks but also in the architectures of RAG systems themselves.<n>We show that near-perfect evaluation scores can be achieved when elements of the evaluation - such as prompt templates or gold nuggets - are leaked or can be predicted.
  arXiv  Detail & Related papers  (2026-01-19T17:03:20Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• An Empirical Study on Failures in Automated Issue Solving [12.571536148821144]
  We analyze the performance and efficiency of three SOTA tools, spanning both pipeline-based and agentic architectures, in automated issue solving tasks of SWE-Bench-Verified.<n>To move from high-level performance metrics to underlying cause analysis, we conducted a systematic manual analysis of 150 failed instances.<n>The results reveal distinct failure fingerprints between the two architectural paradigms, with the majority of agentic failures stemming from flawed reasoning and cognitive deadlocks.
  arXiv  Detail & Related papers  (2025-09-17T13:07:52Z)
• RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning [64.46921169261852]
  RAG-Zeval is a novel end-to-end framework that formulates faithfulness and correctness evaluation as a rule-guided reasoning task.<n>Our approach trains evaluators with reinforcement learning, facilitating compact models to generate comprehensive and sound assessments.<n>Experiments demonstrate RAG-Zeval's superior performance, achieving the strongest correlation with human judgments.
  arXiv  Detail & Related papers  (2025-05-28T14:55:33Z)
• The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models [53.12387628636912]
  We propose an automatic evaluation framework that is validated against human annotations.<n>This approach was originally developed for the TREC Question Answering (QA) Track in 2003.<n>We observe strong agreement at the run level between scores derived from fully automatic nugget evaluation and human-based variants.
  arXiv  Detail & Related papers  (2025-04-21T12:55:06Z)
• Why Do Multi-Agent LLM Systems Fail? [87.90075668488434]
  We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks.<n>We build the first Multi-Agent System Failure taxonomy (MAST)<n>We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent)
  arXiv  Detail & Related papers  (2025-03-17T19:04:38Z)
• Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation [55.21013307734612]
  AoPS-Instruct is a dataset of more than 600,000 high-quality QA pairs.<n>LiveAoPSBench is an evolving evaluation set with timestamps, derived from the latest forum data.<n>Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning.
  arXiv  Detail & Related papers  (2025-01-24T06:39:38Z)
• JuStRank: Benchmarking LLM Judges for System Ranking [7.507819077549208]
  We conduct the first large-scale study of LLM judges as system rankers.<n>System scores are generated by aggregating judgment scores over multiple system outputs.<n>Our analysis provides a fine-grained characterization of judge behavior, including their decisiveness and bias.
  arXiv  Detail & Related papers  (2024-12-12T18:51:13Z)
• Limitations of Automatic Relevance Assessments with Large Language Models for Fair and Reliable Retrieval Evaluation [2.9180406633632523]
  Large language models (LLMs) are gaining much attention as tools for automatic relevance assessment.<n>Recent research has shown that LLM-based assessments yield high systems ranking correlation with human-made judgements.<n>We look at how LLM-generated judgements preserve ranking differences among top-performing systems and also how they preserve pairwise significance evaluation as human judgements.
  arXiv  Detail & Related papers  (2024-11-20T11:19:35Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• tieval: An Evaluation Framework for Temporal Information Extraction Systems [2.3035364984111495]
  Temporal information extraction has attracted a great deal of interest over the last two decades. Having access to a large volume of corpora makes it difficult when it comes to benchmark TIE systems. tieval is a Python library that provides a concise interface for importing different corpora and facilitates system evaluation.
  arXiv  Detail & Related papers  (2023-01-11T18:55:22Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.