Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures

• URL: http://arxiv.org/abs/2607.28802v1
• Date: Thu, 30 Jul 2026 19:55:14 GMT
• Title: Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures
• Abstract summary: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system.<n>This creates a repair-assignment problem: the same visible failure may call for model post-training, harness engineering, environment redesign, or benchmark repair depending on its source.<n>Most failure do little to resolve this problem because they are benchmark-specific and lack a shared structure.<n>We introduce an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component.
• Score: 5.14587904921075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing evaluations often reduce agent failures to system-level outcomes, obscuring where the fault originated and which intervention would improve the agent system. This creates a repair-assignment problem: the same visible failure may call for model post-training, harness engineering, environment redesign, or benchmark repair depending on its source. Because agent behavior emerges from interactions among models, harnesses, users, tools, memory, and environments, outcome-level labels are often insufficient for improvement. Most failure taxonomies do little to resolve this problem because they are benchmark-specific and lack a shared structure. We introduce an interaction-centric taxonomy that localizes failures to the interactions in which they originate and identifies the responsible component. It organizes 41 failure modes by assigning each to an edge between two components and a fault side indicating where the repair belongs. This makes the taxonomy actionable: model-side failures identify targets for post-training, harness-side failures point to scaffolding and tool-integration fixes, and environment or grader failures reveal evaluation conditions requiring redesign. The schema applies across agent architectures, from coding assistants to long-horizon personal assistants and multi-agent systems. We ground the taxonomy in worked examples from public benchmarks, model system cards, published reports, and logged agent trajectories, and evaluate its reproducibility using independent reasoning agents as judges. Across four frontier models, the strongest judge reaches Cohen's $κ=0.76$ against human category labels, suggesting that the categories capture shared structure rather than annotator-specific preferences.

Related papers

• DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems [61.11435469308521]
  We propose DCFA, a training-free framework for failure attribution in large language model systems.<n> DCFA integrates a global module that constructs structured causal-inspired dependency graphs from system traces.<n>Experiments show that DCFA improves step-level accuracy by up to 8.27% over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-09-04T05:29:31Z)
• Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems [16.78530745432555]
  We introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that transforms a failed trace into a structured graph and then navigates it to identify the critical error.<n>Across multiple models, we show that richer trace representations consistently improve failure attribution.<n>This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored.
  arXiv  Detail & Related papers  (2026-08-25T10:18:19Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• A Topology-Aware, Memory-Centric Architecture that Separates Root-Cause Derivation from Root-Cause Explanation [0.0]
  We argue that the missing ingredient in autonomous operations is not a better anomaly detector or a larger language model, but operational memory.<n>We present O PS C ORTEX, a working multi-agent prototype that organizes this memory into four tiers and uses it to separate two tasks the field usually conflates: deriving a root cause and explaining it.
  arXiv  Detail & Related papers  (2026-06-18T09:20:20Z)
• ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures [1.0742675209112622]
  We study failure modes as stemming from three mechanisms: underspecification, capability errors, and agent harness errors.<n>We propose ClayBuddy, a harness that molds to user preferences and can be modified by the model in-session to mitigate these errors.
  arXiv  Detail & Related papers  (2026-06-13T18:29:53Z)
• AgentAtlas: Beyond Outcome Leaderboards for LLM Agents [0.025718125188898048]
  AgentAtlas reframes agent evaluation as a diagnostic vocabulary and audit protocol.<n>The paper contributes: (i) a six-state control-decision taxonomy (Act / Ask / Refuse / Stop / Confirm / Recover); (ii) a trajectory-failure vocabulary with primary error source and downstream impact; and (iv) an illustrative protocol study on a synthetic 1,342-item set evaluated with eight models.
  arXiv  Detail & Related papers  (2026-05-19T22:05:12Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• How to Interpret Agent Behavior [56.59836196946289]
  We introduce ACT*ONOMY, a taxonomy for describing and analyzing agent behavior at runtime.<n>By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently.
  arXiv  Detail & Related papers  (2026-05-13T14:52:40Z)
• Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems [0.0]
  Multi-agent LLM systems fail in production at rates between 41% and 87%, mostly due to coordination defects.<n>We argue that coordination should be treated as a architectural layer, separable from agent logic and from information access.<n>We instantiate this with an information-controlled design on prediction markets.
  arXiv  Detail & Related papers  (2026-05-05T02:56:44Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)

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.