EdgeBench | Scaling Laws of Environment Learning
edge-bench.org · 2,575 words · saved by 2 readers
EdgeBench studies how agents learn from real-world environments across 134 day-long executable tasks.
EdgeBench studies how agents learn from real-world environments across 134 day-long executable tasks. Most benchmarks score what a model already knows. EdgeBench is built to measure something else. It asks how an agent when it is given the time, the feedback, and the room to improve. Every workspace, feedback signal, and judge approximates real practice, so a high score reflects what an agent Each task runs 12+ hours of continuous operation, long enough for experience to compound. Selected extended runs continue Tasks span science, software engineering, optimization, knowledge work, formal mat
saved by
related reading
- ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering | alphaXivalphaxiv.org
- FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale | alphaXivalphaxiv.org
- Senior SWE-Benchsenior-swe-bench.snorkel.ai
- FrontierSWEfrontierswe.com
- PostTrainBenchposttrainbench.com
- Can AI Learn From Experience? EBR-Bench Results | Epoch AI | Epoch AIepoch.ai
- Machine Studying | Jacob Xiaochen Lijacobxli.com
- Continual Learning Bench 1.0 — Newscontinual-learning-bench.com
- AI Agent Benchmark for Real-World Professional Workflowsagents-last-exam.org
- Learning Beyond Gradientstrinkle23897.github.io
- A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
- Quantifying infrastructure noise in agentic coding evals \ Anthropicanthropic.com