When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Attribution

2026-03-18

AI Summary

This work addresses the challenge of attributing responsibility in multi-agent systems when execution logs and agent identifiers are unavailable. The authors propose an implicit execution tracing framework that requires no metadata, embedding decodable signals directly into generated text through key-controlled perturbations of token distributions. This approach enables token-level agent attribution and reconstruction of interaction topologies using only the final output. For the first time, it transforms generated text into a self-describing execution trace without relying on explicit logging, thereby supporting high-precision auditing while preserving privacy. The method maintains both generation quality and interpretability, establishing a novel paradigm for accountable and verifiable multi-agent language systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? Multi-agent language systems increasingly rely on structured interactions such as delegation and iterative refinement, yet the final output often obscures the underlying interaction topology and agent contributions. We introduce IET (Implicit Execution Tracing), a metadata-independent framework that enables token-level attribution directly from generated text and a simple mechanism for interaction topology reconstruction. During generation, agent-specific keyed signals are embedded into the token distribution, transforming the text into a self-describing execution trace detectable only with a secret key. At detection time, a transition-aware scoring method identifies agent handover points and reconstructs the interaction graph. Experiments show that IET recovers agent segments and coordination structure with high accuracy while preserving generation quality, enabling privacy-preserving auditing for multi-agent language systems.

Problem

• multi-agent attribution
• execution tracing
• accountability
• interaction topology
• language systems

Innovation

• Implicit Execution Tracing
• Multi-Agent Attribution
• Token-Level Attribution
• Interaction Topology Reconstruction
• Privacy-Preserving Auditing