📄

Paper

Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

by Hardy Chen arxiv/2604.20200

Free2AITools Nexus Index

38.2

S: Semantic 50

Query-time baseline · scored live at search

A: Authority 0

P: Popularity 0

R: Recency 51

Q: Quality 60

Tech Context

Vital Performance —

Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a public evaluation file with labels in the workspace, rather than through direct inspection of the agent's intermediate outputs. We study whether multi-round user pressure to improve that score induces public score exploitation: behavior that raises the public score through shortcuts without improving hidden private ev...

Source →

- Citations

2026 Year

Paper Information Summary
Entity Passport
Registry ID	2604.20200
License	arXiv
Provider	arxiv

📜

Cite this paper

Academic & Research Attribution

BibTeX

@misc{arxiv_2604_20200,
  author = {Hardy Chen},
  title = {Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows Paper},
  year = {2026},
  howpublished = {\url{https://arxiv.org/abs/2604.20200}},
  note = {Accessed via Free2AITools.}
}

APA Style

Hardy Chen. (2026). Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows [Paper]. Free2AITools. https://arxiv.org/abs/2604.20200

🔬Technical Deep Dive

Full Specifications [+]

⚖️ Free2AITools Nexus Index V2.0

Methodology How FNI works

Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 0

Popularity (P) 0

Recency (R) 51

Quality (Q) 60

💬 Index Insight

FNI V2.0 for Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows: Authority (A:0), Popularity (P:0), Recency (R:51), Quality (Q:60). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

HuggingFace API GitHub Metadata Arxiv Citation DB Methodology

Open data Updated: Live data

📝 Executive Summary

"Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a public evaluation file with labels in the workspace, rather than through direct inspection of the agent's intermediate outputs. We study whether multi-round user pressure to improve that score induces public score exploitation: behavior that raises the public score through shortcuts without improving hidden private ev..."

❝ Cite Node

@article{Chen2026Chasing,
  title={Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows},
  author={Hardy Chen},
  journal={arXiv preprint arXiv:2604.20200},
  year={2026}
}

👥 Collaborating Minds

Hardy Chen

🔗 Full Paper

Free2AITools indexes the abstract and factual metadata for this paper. Read the complete, authoritative paper on the official source.

Read the full paper on arXiv

📊 Research Signals

📅2026Published

⏱️51RecencyFNI pillar

✅60QualityFNI pillar

🗂️cs.CLField

📄 Data Source: arXiv ↗

🔄 Updated daily

Source summary: Based on arXiv metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Paper Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: 2604.20200
slug: 2604.20200
source: arxiv
author: Hardy Chen
license: arXiv
tags: arxiv:cs.CL

📊 Engagement & Metrics

downloads: 0

Data indexed from public sources. Updated daily.