configure
Modify paper discovery and review settings to customize search criteria, ranking weights, notification frequency, and output destinations for automated literature monitoring.
Instructions
Update pipeline configuration.
All parameters are optional — only provided values are changed.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| paper_count_mode | No | "at_most", "at_least", or "exactly" | |
| paper_count_value | No | Number of papers per push (e.g. 6) | |
| custom_focus | No | Custom screening criteria (e.g. "prefer clinical trials over reviews") | |
| review_mode | No | "single" (one AI reviews) or "dual" (two AIs review independently) | |
| w_relevance | No | Ranking weight for topic relevance (default 0.55) | |
| w_recency | No | Ranking weight for publication recency (default 0.20) | |
| w_impact | No | Ranking weight for citation impact (default 0.15) | |
| w_novelty | No | Ranking weight for novelty/unseen (default 0.10) | |
| picks_per_reviewer | No | Papers each reviewer selects per scan (default 5) | |
| scan_batches | No | Number of scan batches per pool cycle (default 2, pool is reviewed over batches+1 days) | |
| site_deploy_hook | No | Vercel deploy hook URL for auto-deploying paper library website | |
| site_repo_path | No | Local path to the paper library site repo (for pushing digest JSON) | |
| summarizer | No | Who handles paper summarization to save tokens. Options: - "self" (default): main agent summarizes (most expensive) - agent name (e.g. "scraper"): delegate to a cheaper agent - API URL: call an external summarization endpoint |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||