RIPPLE: Recovery Internalization through Process-Level Policy Learning and Effect-Aware Credit for Long-Horizon Agentic Coding

No. 233 of 245 · arXiv · Jingxuan Xu, Zihang Xu, Yuechen Luo et al. · published 23 Oct 2026, 04:00 UTC · 35 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

RIPPLE is a training framework for long-horizon coding agents that targets the "Critique-to-Action Handoff Gap," where an agent identifies a failure in a critique but keeps acting on the same incorrect path.

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

Significance0.49
Reader interest0.50
Audience breadth0.51
Practical relevance0.55
Substantiated0.78
Technical depth0.89
New information0.85
Counts against: Promotional0.05
Counts against: Overclaim0.30

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	0.35	—	0.49	0.28	+0.25	+0.122
Reader interest	0.60	0.40	—	0.50	0.20	+0.20	+0.100
Audience breadth	0.56	0.45	—	0.51	0.11	+0.10	+0.051
Practical relevance	0.59	0.50	—	0.55	0.09	+0.15	+0.082
Substantiated	0.95	0.60	—	0.78	0.35	+0.10	+0.078
Technical depth	0.97	0.80	—	0.89	0.17	+0.10	+0.089
New information	0.90	0.80	—	0.85	0.10	+0.10	+0.085
Promotional	0.05	0.05	—	0.05	0.00	−0.15	−0.007
Overclaim	0.25	0.35	—	0.30	0.10	−0.15	−0.045
Sum of contributions							+0.554
Claim-check penalty							0.000
Total, as published							0.554

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.