analiza aiqbench
This survey establishes a critical framework for verifying the internal reasoning and tool-use actions of autonomous LLM agents, moving beyond simple output accuracy to audit execution provenance. By defining methods to trace evidence support and memory lineage, it directly addresses the growing need for accountability in complex multi-agent systems where failures can originate from opaque decision paths. The work provides essential taxonomy and benchmarks necessary for building trustworthy AI infrastructure that can be debugged and recovered when autonomous agents interact with external environments.
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
arXiv:2606.04990v3 Announce Type: replace-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.
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.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2606.04990 [cs.CR]
(or arXiv:2606.04990v3 [cs.CR] for this version)
Text integral sub licența deschisă a publicației · 205 cuvinte
Subiecte conexe
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
arXiv · 16 iun. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026
From Agent Traces to Trust: Evidence Tracing and Execution Provenance in LLM Agents
arXiv · 4 iun. 2026
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
arXiv · 12 sept. 2026