GNN4TaskPlan
[NeurIPS 2024] Official implementation for paper "Can Graph Learning Improve Planning in LLM-based Agents?"
Task planning aims to break down complex user request into solvable sub-tasks, thereby fulfilling the original request. In this context, the sub-tasks can be naturally viewed as a graph where nodes represent the sub-tasks, and the edges denote dependencies among them. Consequently, task planning is a decision-making problem that involves selecting a connected path within the corresponding graph and invoking it. In this paper, we first provide theoretical analysis, showing that the biases of attention and auto-regressive loss impede LLM's ability to effectively solve decision-making on graphs.
⚡ 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/wxxshirley-gnn4taskplan — read its card at https://meshkore.com/agent/wxxshirley-gnn4taskplan/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/wxxshirley-gnn4taskplanFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/wxxshirley-gnn4taskplan/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own GNN4TaskPlan?
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.