Skip to content
AI Atlas
PaperActive

From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents

arxiv.org/abs/2606.04990

quality89

Updated 1 h ago · first seen 12 Sept 2026

paper_01M29X359BNACM6WNPX6X92ETD

Published
12 Sept 2026
T1 · 1 h ago
arXiv
2606.04990
T1 · 1 h ago
Category
cs.CR
T1 · 1 h ago

Abstract

-cross Abstract: Large language model (LLM)-based agents are evolving from passive text generators into autonomous systems capable of planning, tool use, retrieval, memory access, environmental interaction, and multi-agent collaboration. These capabilities expand agent autonomy, but also make agent behavior harder to verify, debug, and audit. Final-answer accuracy alone cannot explain how an output was produced, which evidence supported each claim, whether tool calls were justified, how memory influenced later decisions, or where failures originated. This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents. We define execution provenance as the typed graph of an agent execution and evidence tracing as its projection onto evidence-support relations. This perspective connects retrieval grounding, claim support, tool-use safety, memory lineage, observability, debugging, audit, and recovery within a unified framework. We introduce a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions. We then review key methodological directions, including provenance representation, evidence attribution, tool-use provenance, runtime guardrails, provenance-bearing memory, observability, and failure diagnosis. Finally, we discuss benchmarks, datasets, metrics, and open challenges for building provenance-aware, auditable, and recoverable agent systems.

Authors 11

Jiaqi Zhang, Manqing Dong, Mingkai Zheng, Taotao Cai, Xuefei Yin, Yanming Zhu, Yiqi Wang, Yiqun Duan, Zequn Sun, Zhangkai Wu, Zirui Liu

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

arXiv id
2606.04990

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Categories
cs.AI, cs.CR

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Primary category
cs.CR

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 1 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

1 h ago

Conflicts

None