Prime-RL / verifiers TSP environment (10-city hard config, lenient parser, eval-ready)
-
Updated
Nov 24, 2025 - Python
#
prime-intellect
Here are 4 public repositories matching this topic...
Hybrid CDD RL environment scaffold for Prime Intellect (verifiers + prime-rl).
-
Updated
Mar 2, 2026 - Python
A verifiers RL environment that trains models to propose novel, evidence-grounded, falsifiable hypotheses. Rewards novelty with accountability.
python reinforcement-learning evaluation rl hypothesis-generation tool-use scientific-discovery llm verifiers rlvr prime-intellect
-
Updated
Mar 7, 2026 - Python
A verifiers RLM environment for testing whether adaptive recursive search outperforms brittle manual RAG choreography on long synthetic corpora.
benchmark reinforcement-learning synthetic-data rag tool-use long-context retrieval-augmented-generation llm-evaluation agentic-search verifiers rlvr prime-intellect recursive-language-models
-
Updated
Mar 16, 2026 - Python
Improve this page
Add a description, image, and links to the prime-intellect topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the prime-intellect topic, visit your repo's landing page and select "manage topics."