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

• URL: http://arxiv.org/abs/2603.17445v2
• Date: Thu, 19 Mar 2026 04:14:25 GMT
• Title: When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Attribution
• Abstract summary: We introduce IET (Implicit Execution Tracing), a metadata-independent framework that enables token-level attribution directly from generated text.<n>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.<n>At detection time, a transition-aware scoring method identifies agent handover points and reconstructs the interaction graph.
• Score: 10.973058523304042
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems [36.485119937780524]
  We present Meta-Agent, a two-phase framework that automatically constructs and executes specialized multi-agent systems.<n>We introduce a three-level error attribution mechanism that distinguishes local, upstream, and structural failures.<n>Experiments against strong multi-agent baselines and ablation studies demonstrate consistent improvements in task success rate, error recovery, and workflow stability.
  arXiv  Detail & Related papers  (2026-05-24T19:38:54Z)
• Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction [127.64173950476702]
  We study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools.<n>This approach requires no offline indexing and adapts naturally to evolving local corpora.<n>Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines.
  arXiv  Detail & Related papers  (2026-05-03T19:13:11Z)
• Automated Interpretability and Feature Discovery in Language Models with Agents [3.660409142843126]
  We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models.<n>We show that agent-driven empirical loops yield sharper and more falsifiable explanations than one-shot labels.
  arXiv  Detail & Related papers  (2026-05-02T17:53:30Z)
• Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis [4.365760422569902]
  We introduce an analytics pipeline implemented as part of the Agent Mentor open-source library.<n>It monitors and incrementally adapts the system prompts defining another agent's behavior.<n>The pipeline improves performance by systematically injecting corrective instructions into the agent's knowledge.
  arXiv  Detail & Related papers  (2026-04-12T08:02:54Z)
• Detecting Multi-Agent Collusion Through Multi-Agent Interpretability [0.3467226901703539]
  We introduce NARCBench, a benchmark for evaluating collusion detection under environment distribution shift.<n>We propose five probing techniques that aggregate per-agent deception scores to classify scenarios at the group level.<n>No single probing technique dominates across all collusion types, suggesting that different forms of collusion manifest differently in activation space.
  arXiv  Detail & Related papers  (2026-04-01T17:08:05Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks [0.0]
  This paper proposes a Cross-Agent Multimodal Provenanc- Aware Defense Framework for agentic AI systems.<n>The framework contains a Text sanitizer agent, visual sanitizer agent, and output validator agent all coordinated by a provenance ledger.<n>Experiments show that multimodal injection detection accuracy is significantly enhanced, and the cross-agent trust leakage is minimized.
  arXiv  Detail & Related papers  (2025-12-29T15:54:33Z)
• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection [76.91230292971115]
  Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks.<n>XG-Guard is an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS.
  arXiv  Detail & Related papers  (2025-12-21T13:46:36Z)
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
  This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
  arXiv  Detail & Related papers  (2025-08-13T19:14:48Z)
• Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition [17.451829471077858]
  Cued Speech (CS) is a visual communication system that combines lip-reading with hand coding to facilitate communication for individuals with hearing impairments.<n> Automatic CS Recognition (ACSR) aims to convert CS hand gestures and lip movements into text via AI-driven methods.<n>We propose the first collaborative multi-agent system for ACSR, named Cued-Agent.
  arXiv  Detail & Related papers  (2025-08-01T07:40:39Z)
• SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems [11.497269773189254]
  We present a system-level anomaly detection framework tailored for large language model (LLM)-based multi-agent systems (MAS)<n>We propose a graph-based framework that models agent interactions as dynamic execution graphs, enabling semantic anomaly detection at node, edge, and path levels.<n>Second, we introduce a pluggable SentinelAgent, an LLM-powered oversight agent that observes, analyzes, and intervenes in MAS execution based on security policies and contextual reasoning.
  arXiv  Detail & Related papers  (2025-05-30T04:25:19Z)
• CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems [55.57181090183713]
  We introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought reasoning.<n>Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts.<n>This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios.
  arXiv  Detail & Related papers  (2025-05-26T01:42:37Z)
• GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling [5.798273384241793]
  Large language models (LLMs) enable the development of intelligent agents capable of engaging in complex and multi-turn dialogues.<n>GUARDIAN is a method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs.
  arXiv  Detail & Related papers  (2025-05-25T17:15:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.