arXiv AI
WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 1
Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing
arXiv:2609.39135v1 Announce Type: new Abstract: Physical reasoning from video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreli...
arXiv AI
Aug 21
ChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction
arXiv:2605. 14398v3 Announce Type: replace Abstract: Video-based world models generate visually plausible rollouts, but since they infer dynamics in latent states, they enforce no explicit physical constraints: contacts drift, shapes distort, and motion loses consistency.
arXiv AI
Jun 2
Coding Agent Is Good As World Simulator
arXiv:2605. 14398v2 Announce Type: replace Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics.
arXiv AI
Sep 2
Compositional Machine Design as Program Synthesis with LLMs
arXiv:2510.14980v3 Announce Type: replace Abstract: Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate pro...
arXiv AI
Sep 25
Coding Agents for Generalized Task and Motion Planning Problems
The paper investigates whether large language model–based coding agents can automatically synthesize programs that solve generalized task and motion planning (TAMP) problems across diverse instances. Using Claude Code and Codex, the authors evaluate 980 generated programs on 100 held‑out environments from KinDER and PDDLStream, achieving mean success rates between 56 % and 95 %—higher than hand‑engineered planners and other baselines—while requiring an order of magnitude less computation per instance. The study demonstrates that coding agents can calibrate physical models, test edge cases, and refine strategies, suggesting they are a strong baseline for generalized TAMP.
arXiv AI
Jun 9
SIGA: Self-Evolving Coding-Agent Adapters for Scientific Simulation
arXiv:2606. 09774v1 Announce Type: new Abstract: Advanced scientific simulators expose specialized input languages that turn simulation goals into executable configurations, but learning them can cost domain scientists hours to days.