AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes

No. 165 of 245 · arXiv · Jie Ying, Xutao Zhang, Ningyuan Chen et al. · published 23 Oct 2026, 04:00 UTC · 54 min read

AI & machine learning
Security
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

AgentTriage is a research system that makes security diagnosis of tool-use AI agents replayable across five different agent runtimes, where each diagnostic claim must cite recorded runtime events and the system abstains when evidence is missing.

Read the original at arxiv.org. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.63total under rubric v2.0Contestedjudges differ by 0.48 on reader interest

Significance0.56
Reader interest0.63
Audience breadth0.49
Practical relevance0.65
Substantiated0.73
Technical depth0.90
New information0.90
Counts against: Promotional0.04
Counts against: Overclaim0.22

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.60	0.35	0.72	0.56	0.37	+0.25	+0.140
Reader interest	0.60	0.40	0.88	0.63	0.48 , above the contested threshold	+0.20	+0.125
Audience breadth	0.53	0.40	0.55	0.49	0.15	+0.10	+0.049
Practical relevance	0.71	0.50	0.72	0.65	0.22	+0.15	+0.097
Substantiated	0.98	0.60	0.62	0.73	0.38	+0.10	+0.073
Technical depth	0.98	0.80	0.91	0.90	0.18	+0.10	+0.090
New information	0.86	0.85	0.99	0.90	0.14	+0.10	+0.090
Promotional	0.05	0.05	0.03	0.04	0.02	−0.15	−0.006
Overclaim	0.23	0.30	0.12	0.22	0.18	−0.15	−0.033
Sum of contributions							+0.625
Claim-check penalty							0.000
Total, as published							0.625

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.