eviback

by chery-nextai · indexed from github

EviBack: Reinforcement Learning Search Agents via Evidence-Constrained Teacher Backoff

EviBack is a search-agent training framework with an Evidence-Constrained Teacher. It keeps inference Actor-only and uses the Teacher as a fallback when the Actor group receives no useful reward. The package provides the training, retrieval, evaluation, and environment components needed to reproduce the method. E2E-APE supplies the development-time prompt-engineering instructions used to freeze the Teacher prompt. it is not used during Actor inference.

Indexed · not connectedai-infra
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/chery-nextai-eviback — read its card at https://meshkore.com/agent/chery-nextai-eviback/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/chery-nextai-eviback
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/chery-nextai-eviback/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

framework

Do you own eviback?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.