DeepSearcher stopping-policy experiment

What Jev does in DeepSearcher stopping-policy experiment

The project describes itself this way: Agentic search: a standalone evaluation uses Jev Noul judgments on accumulated evidence to decide whether to stop or continue within a search-round budget, comparing stopping behavior, evidence recall, and decision cost. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

• agent
• agentic-rag
• claude
• deep-research
• deepseek
• deepseek-r1
• grok
• grok3
• llama4
• llm
• milvus
• openai
• qwen3
• rag

How Community additions projects use Jev

Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.

Related Jev projects in Community additions

1. laya-mlxmizorewww/laya-mlxLocal runtime: independent MLX port of the Laya checkpoints that runs typed decisions natively on Apple Silicon — 13.4 ms median end-to-end per short English decision, 7.4 ms with the multilingual checkpoint, and zero output tokens, with no PyTorch, Transformers runtime, or cloud API.★ 5,389
   Python
2. fxvercel-labs/fxCoding agent: ships a `typesafe_permission_reviewer` builtin so the agent's permission decisions run through Jev rather than an LLM call.★ 3,126
   Zig
3. MemSearch Jev rerankingzilliztech/memsearchCoding-agent memory: an optional Jev reranker asks Noul questions about retrieved Markdown chunks and sorts them by relevance to the query, with bilingual evaluation results.★ 2,640
   Python
4. Search with Jev and Milvusmilvus-io/bootcampSearch engineering: nine runnable notebooks combine Gemini embeddings and Milvus retrieval with Jev Noul and Choice judgments, while Python applies ranking, filtering, routing, and stopping policies to synthetic examples.★ 2,445
   Jupyter Notebook
5. minutessilverstein/minutesMeeting notes: local-first transcription app whose live voice path runs its evaluations through Jev.★ 1,494
   Rust
6. v-modal/awesome-jev-toolsv-modal/awesome-jev-toolsTools only, no articles or models.★ 657

See all 156 Community additions projects →

Where we found it

• yibie/awesome-jev