kineticdrive/repro-sciagentgym-benchmarking-multi-step-scientific-tool-use-in-llm-agents-bucket-6 4.02 MB
kineticdrive/repro-sciagentgym-benchmarking-multi-step-scientific-tool-use-in-llm-agents-bucket-5 4.02 MB
kineticdrive/repro-sciagentgym-benchmarking-multi-step-scientific-tool-use-in-llm-agents-bucket-4 4.02 MB
kineticdrive/repro-sciagentgym-benchmarking-multi-step-scientific-tool-use-in-llm-agents-bucket-3 4.02 MB
kineticdrive/repro-sciagentgym-benchmarking-multi-step-scientific-tool-use-in-llm-agents-bucket-2 4.02 MB
Running Reproduction: LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory 🎯 Explore project logs, traces, and workspace in a web UI
Running Reproduction: OUSAC: Optimized gUidance Scheduling with Adaptive Caching 🎯 Explore experiment logs, code, and traces in a collaborative web view
Running Reproduction: AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design 🎯 Explore project logs and traces in an interactive workspace
Running Reproduction: Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space 🎯 Explore and manage experiment logs with AI collaboration
Running PFT phonon fine-tuning reproduction 🎯 Explore code, traces, and workspace in an interactive logbook
Running Reproduction: CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation 🎯 Explore and collaborate on robot coding logs in a web interface