WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?

Key points

• As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time.1
• Building such solvers requires physical understanding to identify appropriate models, mathematical reasoning to formulate the underlying dynamics, and software engineering to implement them as executable code, yet this capability of LLM agents remains underexplored.1
• To this end, we introduce WorldSolver, a benchmark of 168 simulation tasks derived from physical phenomena in 61 classic computer graphics papers, spanning 7 physical domains.1
• WorldSolver is an early step toward agentic solver generation, and we hope it helps drive progress toward agents that can faithfully simulate the dynamic physical world.1

Sources (1)

• [1]WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:26 PM

  LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films.

  As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time.

Extractive summary: sentences quoted from the sources.