# LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents

arXiv: https://arxiv.org/abs/2608.18398 · HTML: https://mlsanity.com/paper/2608.18398/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents](https://mlsanity.com/paper/2506.00641/) (2025)
- [Monitoring Monitorability](https://mlsanity.com/paper/2512.18311/) (2025)
- [PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows](https://mlsanity.com/paper/2508.02866/) (2025)
- [Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models](https://mlsanity.com/paper/2412.03801/) (2024)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [CodeTracer: Towards Traceable Agent States](https://mlsanity.com/paper/2604.11641/) (2026)
- [TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems](https://mlsanity.com/paper/2605.26563/) (2026)
- [DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning](https://mlsanity.com/paper/2508.01700/) (2025)
- [The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science](https://mlsanity.com/paper/2509.09915/) (2025)
- [Provenance Tracking in Large-Scale Machine Learning Systems](https://mlsanity.com/paper/2507.01075/) (2025)
- [Graph of Trace: Visualizing Execution Traces of Scientific Agent](https://mlsanity.com/paper/2606.15116/) (2026)
- [When the Chain Breaks: Interactive Diagnosis of LLM Chain-of-Thought Reasoning Errors](https://mlsanity.com/paper/2603.21286/) (2026)

## Built on by (most cited first, 5 of 5)

- [Quantifying Overclaiming Propensity in Frontier LLM Agents](https://mlsanity.com/paper/2609.20812/) (2026)
- [Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents](https://mlsanity.com/paper/2609.12205/) (2026)
- [Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records](https://mlsanity.com/paper/2609.17631/) (2026)
- [Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression](https://mlsanity.com/paper/2609.31683/) (2026)
- [Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs](https://mlsanity.com/paper/2609.38266/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As agents do more work faster, the productivity bottleneck shifts from producing outputs to auditing whether those outputs are correct and trustworthy. Agent observability systems make fine-grained execution events visible, but visibility alone still leaves reviewers to reconstruct which actions, artifacts, and validation steps matter for a particular conclusion. We introduce LEDGER - Layered Evidence and Decision Graphs for Execution Review, a tracing and review system that builds layered trace graphs over observed agent sessions. LEDGER preserves Trace Records while grouping them into Evidence Nodes and Workflow Nodes, representing artifacts as evidence anchors, and adding typed semantic edges that connect claims to supporting actions, artifacts, and checks. Through data-analysis and coding examples, we show how the resulting traces expose workflow decisions, artifact lineage, repair steps, validation coverage, and claim-support paths for evidence-centered audit.