AgentBench

FutureHouse is a nonprofit AI research lab focused on automating scientific discovery in biology and other complex sciences. FutureHouse features superintelligent AI agents designed to assist scientists in accelerating research processes. It is optimized for retrieving and summarizing information from scientific literature, achieving state-of-the-art performance on benchmarks like RAG-QA Arena's science benchmark. It employs an agentic approach, allowing for iterative query expansion, LLM re-ranking, contextual summarization, and document citation traversal to enhance retrieval accuracy. FutureHouse also offers a framework for training language agents on challenging scientific tasks, enabling agents to perform tasks such as protein engineering, literature summarization, and molecular cloning. Their LAB-Bench benchmark evaluates language models on biology research tasks, including information extraction, database retrieval, etc.

Maxim is an agent simulation, evaluation, and observability platform that empowers modern AI teams to deploy agents with quality, reliability, and speed. Maxim's end-to-end evaluation and data management stack covers every stage of the AI lifecycle, from prompt engineering to pre & post release testing and observability, data-set creation & management, and fine-tuning. Use Maxim to simulate and test your multi-turn workflows on a wide variety of scenarios and across different user personas before taking your application to production. Features: Agent Simulation Agent Evaluation Prompt Playground Logging/Tracing Workflows Custom Evaluators- AI, Programmatic and Statistical Dataset Curation Human-in-the-loop Use Case: Simulate and test AI agents Evals for agentic workflows: pre and post-release Tracing and debugging multi-agent workflows Real-time alerts on performance and quality Creating robust datasets for evals and fine-tuning Human-in-the-loop workflows