Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

About

"Code-as-Policy" considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying levels of abstraction, interaction, and perceptual grounding. Across 12 models, CaP-Bench reveals a consistent trend: performance improves with human-crafted abstractions but degrades as these priors are removed, exposing a dependence on designer scaffolding. At the same time, we observe that this gap can be mitigated through scaling agentic test-time computation--through multi-turn interaction, structured execution feedback, visual differencing, automatic skill synthesis, and ensembled reasoning--substantially improves robustness even when agents operate over low-level primitives. These findings allow us to derive CaP-Agent0, a training-free framework that recovers human-level reliability on several manipulation tasks in simulation and on real embodiments. We further introduce CaP-RL, showing reinforcement learning with verifiable rewards improves success rates and transfers from sim2real with minimal gap. Together, CaP-X provides a principled, open-access platform for advancing embodied coding agents.

Letian Fu, Justin Yu, Karim El-Refai, Ethan Kou, Haoru Xue, Huang Huang, Wenli Xiao, Guanzhi Wang, Dantong Niu, Fei-Fei Li, Guanya Shi, Jiajun Wu, Shankar Sastry, Yuke Zhu, Ken Goldberg, Linxi "Jim" Fan• 2026

Related benchmarks

TaskDatasetResultRank
Robot ManipulationLIBERO Object--
139
Robotic ManipulationLIBERO Goal
Positional Success Rate66
55
Robot ManipulationLIBERO-PRO
Task Perturbation Goal SR17
22
Robotic ManipulationLIBERO-PRO Spatial
Success Rate (Pos)12
12
Open-vocabulary long-horizon manipulationRoboVoLo Common Sense Suite
Infer Rate14.29
11
Open-vocabulary long-horizon manipulationRobolab-Vague
Success Rate (Easy)16.67
11
Open-vocabulary long-horizon manipulationRoboVoLo Memory Suite
Order Score16.67
11
Open-vocabulary long-horizon manipulationRoboVoLo Complex References Suite
Spatial Performance7.41
11
Open-vocabulary long-horizon manipulationRoboVoLo World Knowledge Suite
Art Success Rate0.00e+0
11
Robotic ManipulationLIBERO-PRO six position-and-task cells
Object Positional Success Rate22
10
Showing 10 of 48 rows

Other info

Follow for update