• 🎯 Aim
• 📚 Definitions
• 🦾 Code as Policy
• 🗺️ Code as World
• 🧮 Programmable World Models
• ✂️ Edit Graph
• 📊 Benchmark
  • Policy programs
  • World programs
  • Robot evaluation infrastructure
• 📚 Surveys and Lessons
• 🛠️ Projects
  • Eval reports
  • Policy programs in simulation
  • Policy programs on a real robot
  • Plan, then call a VLA
  • World programs from video
  • RL training stacks
  • Scene programs
• 🔗 Related Resources

We collect papers where an agent writes or edits a program, a tool graph, or an explicit world state, then a simulator, renderer, robot, or editor runs it. That includes robot policies, executable scenes, programmable world models, image or video edit graphs, and benchmarks for those agents. Systems, evals, and case catalogs without a paper go under Projects, not under the paper sections.

New papers and projects get added as they appear. PRs are welcome.

• Policy program
• World program
• Programmable world model
• Edit graph
• Benchmark
• Project

Policy program. A Code-as-Policy agent is an LLM or VLM that writes executable robot programs, or a thin semantic action interface. That is the alternative to VLA action tokens. The name comes from Code as Policies.

• [⭐️] Code as Policies: Language Model Programs for Embodied Control.

World program. A world program is an executable scene or physics program in Blender, MuJoCo, USD, CadQuery, or a similar stack. It is not a static mesh and not a video. Generation writes the program from language or a layout. Inversion / Reconstruction writes it from images, video, or scans.

• [⭐️] SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects.

Physical Coding, from Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence, also uses Code as World for symbolic robot task state: objects, relations, constraints, observations, and progress predicates. That is separate from the executable scene programs grouped below; see