Automating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash

No. 235 of 245 · arXiv · Atharv Chandratre, Jai Datar · published 23 Oct 2026, 04:00 UTC · 18 min read

Programming & dev tools
AI & machine learning
Paper

2 judges. Scored by two of the three judges. The third reads only the day’s strongest candidates. How far stories are checked

DoorDash describes a multi-agent LLM system built on Google ADK that automates removal of stale feature flags (called Dynamic Values internally) across its codebases, where roughly 1,659 stale flags remain and manual cleanup takes one to two hours each.

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

0.55total under rubric v2.0

Significance0.46
Reader interest0.68
Audience breadth0.38
Practical relevance0.73
Substantiated0.71
Technical depth0.78
New information0.81
Counts against: Promotional0.11
Counts against: Overclaim0.39

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	0.63	0.30	—	0.46	0.33	+0.25	+0.116
Reader interest	0.75	0.60	—	0.68	0.15	+0.20	+0.135
Audience breadth	0.36	0.40	—	0.38	0.04	+0.10	+0.038
Practical relevance	0.85	0.60	—	0.73	0.26	+0.15	+0.109
Substantiated	0.92	0.50	—	0.71	0.42 , above the contested threshold	+0.10	+0.071
Technical depth	0.96	0.60	—	0.78	0.36	+0.10	+0.078
New information	0.91	0.70	—	0.81	0.21	+0.10	+0.081
Promotional	0.07	0.15	—	0.11	0.08	−0.15	−0.017
Overclaim	0.43	0.35	—	0.39	0.08	−0.15	−0.058
Sum of contributions							+0.553
Claim-check penalty							0.000
Total, as published							0.553

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested. Judge 3 did not score this story; its mean uses the other two.

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.