Coding Agents for Generalized Task and Motion Planning Problems
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - Coding agents can synthesize reusable programs for generalized task and motion planning, outperforming traditional planners and LLM baselines across simulated robotics environments. The results suggest agent-written code is a strong, compute-efficient baseline for solving unseen planning instances with less domain-specific engineering.
- Claude Code and Codex agents generated 980 programs across 28 KinDER and PDDLStream environments, evaluated over 98,000 held-out episodes.
- Agent configurations achieved 56%–95% mean success, versus 47% for hand-engineered planners on the 16 environments where planners were available.
- Generated programs maintained higher success as object counts increased while using roughly an order of magnitude less computation per instance.
- Agent logs showed iterative simulator use to calibrate physical models, test edge cases, and refine planning strategies.
Sources (1)
Coding Agents for Generalized Task and Motion Planning Problems
TL;DR - Coding agents can synthesize reusable programs for generalized task and motion planning, outperforming traditional planners and LLM baselines across simulated robotics environments. The results suggest agent-written code is a strong, compute-efficient baseline for solving unseen planning instances with less domain-specific engineering.
- Claude Code and Codex agents generated 980 programs across 28 KinDER and PDDLStream environments, evaluated over 98,000 held-out episodes.
- Agent configurations achieved 56%–95% mean success, versus 47% for hand-engineered planners on the 16 environments where planners were available.
- Generated programs maintained higher success as object counts increased while using roughly an order of magnitude less computation per instance.
- Agent logs showed iterative simulator use to calibrate physical models, test edge cases, and refine planning strategies.