๐Ÿ“–
AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
Jie Ying, Xutao Zhang, Ningyuan Chen, Mengce Zheng, Jun Li, Zhongjie Zhu, Tiantian Zhu

AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence through incompatible interfaces. We present AgentTriage, an executable contract for replayable security diagnosis across heterogeneous runtimes. The contract admits conclusions whose claims cite canonical runtime events and requires abstention when mandatory evidence is missing. Runtime overlays normalize native observations, while a deterministic pipeline joins invocation and result lifecycles, constructs a typed provenance graph, selects a policy-decisive slice, and binds claims to recorded evidence. Given the same normalized trace, overlay version, and pre-run policy oracle, the diagnosis can be recomputed and its claims re-checked without language-model judgment. Across five runtimes, one contract captures all 159 applicable executions, with an audit of native and synthesized identifiers. On 120 adjudicated cases, AgentTriage achieves 0.858 grounded joint diagnosis, 0.966 required-evidence coverage, and a 0.036 unsupported-claim rate, improving joint diagnosis by 0.175 (95% CI [0.092, 0.258]) over the strongest same-schema baseline. These results quantify the precision of replayable diagnosis and the observation boundaries that require abstention. We release an open-source implementation and selected sanitized evidence at https://github.com/AsnGs/agenttriage-open-source.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
Author / Organization Jie Ying, Xutao Zhang, Ningyuan Chen, Mengce Zheng, Jun Li, Zhongjie Zhu, Tiantian Zhu
Subject & Discipline cs.AI
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-265188
Original Source Link Visit Source Page on arxiv.org »