Skip to content
← Back to explorer

Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents

Raffi Khatchadourian · Jan 17, 2026 · Citations: 0

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 7, 2026, 8:27 PM

Recent

Extraction refreshed

Mar 14, 2026, 5:03 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.45

Abstract

LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results. We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in tool-using agents deployed in financial services. Across 4,700+ agentic runs (7 models, 4 providers, 3 financial benchmarks with 50 cases each at T=0.0), we find that decision determinism and task accuracy are not detectably correlated (r = -0.11, 95% CI [-0.49, 0.31], p = 0.63, n = 21 configurations): models can be deterministic without being accurate, and accurate without being deterministic. Because neither metric predicts the other in our sample, both must be measured independently, which is precisely what DFAH provides. Small models (7-20B) achieve near-perfect determinism through rigid pattern matching at the cost of accuracy (20-42%), while frontier models show moderate determinism (50-96%) with variable accuracy. No model achieves both perfect determinism and high accuracy, supporting DFAH's multi-dimensional measurement approach. We provide three financial benchmarks (compliance triage, portfolio constraints, and DataOps exceptions; 50 cases each) together with an open-source stress-test harness. Across these benchmarks and DFAH evaluation settings, Tier 1 models with schema-first architectures achieved determinism levels consistent with audit replay requirements.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction confidence is 0.45 (below strong-reference threshold).

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction confidence is 0.45 (below strong-reference threshold).

Trust level

Low

Eval-Fit Score

25/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.

Reported Metrics

partial

Accuracy, Cost, Faithfulness

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in tool-using agents deployed in financial services.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Trajectory
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: Long Horizon
  • Quality controls: Not reported
  • Confidence: 0.45
  • Flags: ambiguous

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracycostfaithfulness

Research Brief

Deterministic synthesis

LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results. HFEPX signals include Automatic Metrics, Long Horizon with confidence 0.45. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 5:03 AM · Grounded in abstract + metadata only

Key Takeaways

  • LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.
  • We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy, cost, faithfulness).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, many deployments fail to return consistent results.
  • We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in tool-using agents deployed in financial services.
  • Across 4,700+ agentic runs (7 models, 4 providers, 3 financial benchmarks with 50 cases each at T=0.0), we find that decision determinism and task accuracy are not detectably correlated (r = -0.11, 95% CI [-0.49, 0.31], p = 0.63, n = 21…

Why It Matters For Eval

  • We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism, decision determinism, and evidence-conditioned faithfulness in tool-using agents deployed in financial services.
  • Across 4,700+ agentic runs (7 models, 4 providers, 3 financial benchmarks with 50 cases each at T=0.0), we find that decision determinism and task accuracy are not detectably correlated (r = -0.11, 95% CI [-0.49, 0.31], p = 0.63, n = 21…

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy, cost, faithfulness

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.