AI News HubLIVE
Original source2 min read

Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

This paper presents RubricForge, which automatically induces human-readable judging rubrics from a small set of ground-truth-labeled agent trajectories. In evaluations with a frozen 7B model on tau-bench and WebShop, it reduces false-pass rates (e.g., 0.115 vs 0.173 on tau-bench) and improves ranking faithfulness relative to a generic G-Eval judge, while keeping verdicts attributable to named criteria. Its aggregate agreement gain is not statistically significant, and absolute-score calibration is slightly worse.

SourcearXiv AIAuthor: Darragh Quinn, David Dylan, Roisin Healy, Fionn Carroll, Maeve Donnelly, Cormac Sheehan

-->

[Submitted on 25 Jun 2026]

Title:Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

View a PDF of the paper titled Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation, by Darragh Quinn and 5 other authors

View PDF HTML (experimental)

Abstract:Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time. Such a judge is a reward-free proxy whose value depends on whether it can be trusted, yet existing judges either hand-write the scoring rubric, as in G-Eval, or fine-tune the judge's weights, and both tend to credit fluent but unsuccessful trajectories as successes. We instead induce the text of an agent-judging rubric from a small set of ground-truth-labeled trajectories, grounding it in true outcomes. We present RubricForge, which evolves a judge rubric by reflective evolution against labeled trajectories to maximize agreement with the environment reward, freezes it, and applies it to held-out trajectories in one model call with no environment access. The optimized artifact is human-readable text, so every verdict is attributable to named criteria. Using one frozen 7B model as both agent and judge, on tau-bench (173 labeled trajectories drawn from 220 rollouts) and WebShop (160), the principal gain is faithfulness rather than raw agreement. The edge over a generic G-Eval judge is not statistically significant (McNemar p = 0.248), and absolute-score calibration marginally favors the generic judge (|err| difference -0.048, p = 2x10^-4). Yet RubricForge over-credits failed trajectories roughly half as often (0.115 vs. 0.173 false-pass rate on tau-bench, with three over-credit catches and zero reversals) and ranks graded WebShop outcomes more faithfully (Spearman 0.410 vs. 0.370). For a reward-free evaluator the false-pass rate, not aggregate agreement, is the deployment-relevant quantity, since a false pass ships a broken agent whereas a false fail merely costs a retry.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2608.13564 [cs.AI]

(or arXiv:2608.13564v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.13564

arXiv-issued DOI via DataCite

Submission history

From: Dylan David [view email] [v1] Thu, 25 Jun 2026 03:58:31 UTC (1,494 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation, by Darragh Quinn and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-08

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)