Yadong Mu, Zhicheng Sun, Jinghan Li
We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| singularity0104/equilibrium-planner | canonical | 3 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| copy_cache | Ran | singularity0104/equilibrium-planner/equilibrium_model/generate_equilibrium.py pointer only (licence: NONE) · get_code("e8f31ad2b152353d") |
| generate_prefix_cache | Ran | singularity0104/equilibrium-planner/equilibrium_model/generate_equilibrium.py pointer only (licence: NONE) · get_code("7b29b0c60dd71450") |
| generate_use_cache | Ran | singularity0104/equilibrium-planner/equilibrium_model/generate_equilibrium.py pointer only (licence: NONE) · get_code("2d5e489b631a7bf6") |
| generate_equilibrium_cached | Not yet run | singularity0104/equilibrium-planner/equilibrium_model/generate_equilibrium.py pointer only (licence: NONE) · get_code("5839a7ff0381f6cf") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions to long-horizon action sequences. Despite recent advances in language model agents, they remain prone to planning errors and limited in their ability to plan ahead. To address these limitations in robotic planning, we advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached. Remarkably, this process can be optimized end-to-end from an analytical perspective without the need to curate additional verifiers or reward models, allowing us to train self-refining planners in a simple supervised learning fashion. Meanwhile, a nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning that incorporates useful feedback from the environment (or an internal world model). Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with improved scaling w.r.t. inference-time computation. Code is available at https: //github.com/Singularity0104/ equilibrium-planner.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.01440")
get_code_for_paper("2410.01440")
have("2410.01440")
Connect an agent — have() is free.