LAT
Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning (Poster of AAAI'26)
TL;DR: In this paper, we introduce the Chain of Evidence (CoE) paradigm, which models stepwise inference by grounding each chain-of-thought (CoT) reasoning step. To realize CoE, we propose Look As You Think (LAT), a two-stage reinforcement learning (RL) framework that trains VLMs to unify CoT reasoning and visual grounding by generating progressive reasoning process paired with an aligned visual attribution for each reference element.
⚡ 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/mine-ustc-lat — read its card at https://meshkore.com/agent/mine-ustc-lat/.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.
https://meshkore.com/agent/mine-ustc-latFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/mine-ustc-lat/.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
Do you own LAT?
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.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.