RRepoGEO

REPOGEO REPORT · LITE

test-time-training/discover

Default branch main · commit 6c40e82d · scanned 6/9/2026, 12:57:31 AM

GitHub: 580 stars · 80 forks

AI VISIBILITY SCORE
23 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

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 test-time-training/discover, 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

2 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highabout#1
    Add a concise repository description

    Why:

    COPY-PASTE FIX
    A framework for Test-Time Training (TTT) that uses reinforcement learning to adapt Large Language Models (LLMs) for specific problems during inference, achieving state-of-the-art results.
  • highreadme#2
    Refine the README's opening statement for clearer positioning

    Why:

    CURRENT
    TTT-Discover performs reinforcement learning at test time, allowing the LLM to continue training with experience specific to the problem at hand. We achieve new state-of-the-art across mathematics, GPU kernels, algorithms, and biology.
    COPY-PASTE FIX
    TTT-Discover is a novel framework that applies reinforcement learning at test time, enabling Large Language Models (LLMs) to continuously adapt and improve on specific problems during inference. It achieves new state-of-the-art across mathematics, GPU kernels, algorithms, and biology by allowing LLMs to learn from experience specific to the problem at hand.

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.

Recall
0 / 2
0% of queries surface test-time-training/discover
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
langchain-ai/langchain
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. langchain-ai/langchain · recommended 1×
  2. run-llama/llama_index · recommended 1×
  3. UKPLab/sentence-transformers · recommended 1×
  4. facebookresearch/faiss · recommended 1×
  5. huggingface/peft · recommended 1×
  • CATEGORY QUERY
    How to continuously adapt a large language model for specific problems during inference?
    you: not recommended
    AI recommended (in order):
    1. LangChain (langchain-ai/langchain)
    2. LlamaIndex (run-llama/llama_index)
    3. Sentence Transformers (UKPLab/sentence-transformers)
    4. Faiss (facebookresearch/faiss)
    5. Hugging Face PEFT Library (huggingface/peft)
    6. Axolotl (OpenAccess-AI-Collective/axolotl)
    7. TRL (Transformer Reinforcement Learning) from Hugging Face (huggingface/trl)

    AI recommended 7 alternatives but never named test-time-training/discover. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a framework for real-time model improvement using reinforcement learning on new data.
    you: not recommended
    AI recommended (in order):
    1. Ray RLlib (ray-project/ray)
    2. Acme (deepmind/acme)
    3. TF-Agents (tensorflow/agents)
    4. OpenAI Baselines (openai/baselines)
    5. Stable Baselines3 (DLR-RM/stable-baselines3)

    AI recommended 5 alternatives but never named test-time-training/discover. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    fail

    Suggestion:

  • README presence
    pass

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 test-time-training/discover?
    pass
    AI named test-time-training/discover explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts test-time-training/discover in production, what risks or prerequisites should they evaluate first?
    pass
    AI named test-time-training/discover 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 test-time-training/discover solve, and who is the primary audience?
    pass
    AI did not name test-time-training/discover — 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 test-time-training/discover. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/test-time-training/discover.svg)](https://repogeo.com/en/r/test-time-training/discover)
HTML
<a href="https://repogeo.com/en/r/test-time-training/discover"><img src="https://repogeo.com/badge/test-time-training/discover.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

test-time-training/discover — 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
test-time-training/discover — RepoGEO report