REPOGEO REPORT · LITE
YennNing/Awesome-Code-as-Agent-Harness-Papers
Default branch main · commit 06b0d447 · scanned 6/28/2026, 4:02:55 PM
GitHub: 519 stars · 40 forks
Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface YennNing/Awesome-Code-as-Agent-Harness-Papers, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.
Action plan — copy-paste fixes
3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.
- hightopics#1Add relevant topics to the repository
Why:
COPY-PASTE FIXawesome-list, research-papers, ai-agents, code-as-agent, generative-ai, llm-agents, machine-learning, survey, agentic-ai
- highreadme#2Clarify the repository's type as a curated list in the README's opening
Why:
CURRENT# Awesome Code as Agent Harness Papers This repository accompanies the survey **Code as Agent Harness: Toward Executable, Verifiable, and Stateful Agent Systems**.
COPY-PASTE FIX# Awesome Code as Agent Harness Papers This is a curated list of research papers and resources, accompanying the survey **Code as Agent Harness: Toward Executable, Verifiable, and Stateful Agent Systems**.
- mediumhomepage#3Add the survey's official webpage as the repository homepage
Why:
COPY-PASTE FIXhttps://code-as-harness.github.io/code-as-harness-webpage/
Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash
Category visibility — the real GEO test
Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?
Same questions for every model — switch tabs to compare answers and rankings.
- XState · recommended 1×
- SCXML · recommended 1×
- BehaviorTree.CPP · recommended 1×
- py_trees · recommended 1×
- Gymnasium · recommended 1×
- CATEGORY QUERYHow to design AI agents with executable, verifiable, and stateful control mechanisms?you: not recommendedAI recommended (in order):
- XState
- SCXML
- BehaviorTree.CPP
- py_trees
- Gymnasium
- Stable Baselines3
- Ray RLlib
- Prolog
- Datalog
- RxJS
- Akka Streams
AI recommended 11 alternatives but never named YennNing/Awesome-Code-as-Agent-Harness-Papers. This is the gap to close.
Show full AI answer
- CATEGORY QUERYWhere can I find research on using code to build robust and inspectable AI agent systems?you: not recommendedAI recommended (in order):
- arXiv.org
- Google Scholar
- ACL Anthology
- NeurIPS
- ICML
- ICLR
- PMLR (Proceedings of Machine Learning Research)
- AAAI
- IJCAI
- ACM Digital Library
- IEEE Xplore
- Journal of Artificial Intelligence Research (JAIR)
AI recommended 12 alternatives but never named YennNing/Awesome-Code-as-Agent-Harness-Papers. This is the gap to close.
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesswarn
Suggestion:
- README presencepass
Self-mention check
Does AI even know your repo exists when asked about it directly?
- Compared to common alternatives in this category, what is the core differentiator of YennNing/Awesome-Code-as-Agent-Harness-Papers?passAI did not name YennNing/Awesome-Code-as-Agent-Harness-Papers — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- If a team adopts YennNing/Awesome-Code-as-Agent-Harness-Papers in production, what risks or prerequisites should they evaluate first?passAI named YennNing/Awesome-Code-as-Agent-Harness-Papers explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- In one sentence, what problem does the repo YennNing/Awesome-Code-as-Agent-Harness-Papers solve, and who is the primary audience?passAI did not name YennNing/Awesome-Code-as-Agent-Harness-Papers — likely talking about a different project
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
Embed your GEO score
Drop this badge into the README of YennNing/Awesome-Code-as-Agent-Harness-Papers. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
[](https://repogeo.com/en/r/YennNing/Awesome-Code-as-Agent-Harness-Papers)<a href="https://repogeo.com/en/r/YennNing/Awesome-Code-as-Agent-Harness-Papers"><img src="https://repogeo.com/badge/YennNing/Awesome-Code-as-Agent-Harness-Papers.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
YennNing/Awesome-Code-as-Agent-Harness-Papers — Lite scans stay free; this card itemizes Pro deep limits vs Lite.
- Deep reports10 / month
- Brand-free category queries5 vs 2 in Lite
- Prioritized action items8 vs 3 in Lite