Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents

• URL: http://arxiv.org/abs/2604.16752v1
• Date: Fri, 17 Apr 2026 23:54:34 GMT
• Title: Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents
• Abstract summary: We introduce the Support-State Triage Audit (SSTA-32), a matched-item diagnostic framework in which minimal counterfactual edits flip the same base request across four support states.<n>We evaluate a frontier model under four prompting conditions using Dual-Persona Auto-Auditing (DPAA) with deterministic scoring.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current agent evaluations largely reward execution on fully specified tasks, while recent work studies clarification [11, 22, 2], capability awareness [9, 1], abstention [8, 14], and search termination [20, 5] mostly in isolation. This leaves open whether agents can diagnose why a task is blocked before acting. We introduce the Support-State Triage Audit (SSTA-32), a matched-item diagnostic framework in which minimal counterfactual edits flip the same base request across four support states: Complete (ANSWER), Clarifiable (CLARIFY), Support-Blocked (REQUEST SUPPORT), and Unsupported-Now (ABSTAIN). We evaluate a frontier model under four prompting conditions - Direct, Action-Only, Confidence-Only, and a typed Preflight Support Check (PSC) - using Dual-Persona Auto-Auditing (DPAA) with deterministic heuristic scoring. Default execution overcommits heavily on non-complete tasks (41.7% overcommitment rate). Scalar confidence mapping avoids overcommitment but collapses the three-way deferral space (58.3% typed deferral accuracy). Conversely, both Action-Only and PSC achieve 91.7% typed deferral accuracy by surfacing the categorical ontology in the prompt. Targeted ablations confirm that removing the support-sufficiency dimension selectively degrades REQUEST SUPPORT accuracy, while removing the evidence-sufficiency dimension triggers systematic overcommitment on unsupported items. Because DPAA operates within a single context window, these results represent upper-bound capability estimates; nonetheless, the structural findings indicate that frontier models possess strong latent triage capabilities that require explicit categorical decision paths to activate safely.

Related papers

• SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents [56.400332595452966]
  We introduce SearchAuditBench, a benchmark that evaluates whether auditors can localize, attribute, and repair search-agent failures.<n>SearchAuditBench comprises 1,243 failed trajectories, averaging 73.1 messages and 65.1K tokens, collected from eight open-weight models on five deep-search benchmarks.<n>We propose SearchAuditor, a multi-perspective auditing framework that effectively localizes, attributes, and repairs search-agent failures.
  arXiv  Detail & Related papers  (2026-08-05T09:09:00Z)
• AgentAbstain: Do LLM Agents Know When Not to Act? [19.223843408018997]
  Existing evaluations mostly focus on task success rather than whether agents know when to abstain.<n>We present the first systematic evaluation framework for agentic abstention: the calibrated ability of tool-using LLM agents to recognize when not to act.<n>AgentAbstain is a paired-task benchmark built on an agent-native taxonomy of 8 abstention scenarios across pre-execution reasoning and runtime discovery.
  arXiv  Detail & Related papers  (2026-07-11T00:57:36Z)
• Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents [4.309840398782996]
  In hierarchical reasoning, failures often originate at intermediate decision points where the agent commits to a wrong branch.<n>We propose ACTION-RATING, a formulation that places clarification inside the agent's action space on a shared ordinal scale with navigation.<n>Two structurally distinct information-seeking modes emerge from the agent's own ratings: mandatory (no viable branch) and opportunistic (residual uncertainty despite a leading candidate)
  arXiv  Detail & Related papers  (2026-06-09T18:25:57Z)
• Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework [9.601233098598456]
  This study proposes a unified multi-dimensional framework for measuring reasoning quality in LLMs from a behavioral perspective.<n>Experiments on seven LLMs across 975 items from four benchmarks demonstrate that the framework reveals behaviors invisible to accuracy-only metrics.
  arXiv  Detail & Related papers  (2026-05-23T17:03:42Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance [0.0]
  We tested whether symptom validity testing logic could identify sandbagging through below-chance performance (BCB) on forced-choice items.<n>We found zero of 12 model-domain cells showed significant below-chance performance under sandbagging instruction.<n>We propose that positional-distribution shift may be a more effective behavioural signature than below-chance accuracy for detecting prompted underperformance at this model scale.
  arXiv  Detail & Related papers  (2026-04-28T05:57:23Z)
• Harness as an Asset: Enforcing Determinism via the Convergent AI Agent Framework (CAAF) [0.0]
  Convergent Agent Framework (CAAF) transitions agentic from open-loop generation to closed-loop Fail-Safe Determinism.<n>CAAF's reliability is invariant to prompt hints; all components use a single commodity model, enabling fully offline deployment.
  arXiv  Detail & Related papers  (2026-04-18T15:15:09Z)
• Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis [0.0]
  We build a unified cross-language vulnerability lifecycle framework for software vulnerability analysis.<n>We achieve 89.84-92.02% intra-language detection accuracy and 74.43-80.12% zero-shot cross-language F1.<n>These results demonstrate that execution-grounded closed-loop reasoning is a principled and practically deployable mechanism for trustworthy LLM-driven agentic AI.
  arXiv  Detail & Related papers  (2026-04-12T20:22:23Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs [51.56484100374058]
  guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency.<n>We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks.<n>Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR.
  arXiv  Detail & Related papers  (2026-03-29T18:52:01Z)
• Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes [37.92248202525651]
  We propose a Dual-Stage Intent-Aware (DS-IA) Framework to separate high-level user intent understanding from low-level physical execution.<n>Tests show DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%.
  arXiv  Detail & Related papers  (2026-03-17T07:38:39Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)

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.