caixd-220529/LifelongAgentBench
Code repo for "LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners"
This project helps AI researchers and developers evaluate how well large language model (LLM) agents learn continuously over time. It takes various LLM agents and scenarios (like database interactions or operating system tasks) as input, and outputs performance metrics that show if agents can retain knowledge and adapt to new information. Anyone working on building more robust and adaptable AI agents for real-world applications would use this.
No commits in the last 6 months.
Use this if you need to systematically test and benchmark the 'lifelong learning' capabilities of your LLM agents across diverse environments and tasks.
Not ideal if you are looking for a tool to build or deploy LLM agents for specific applications, rather than evaluate their learning capabilities.
Stars
80
Forks
5
Language
Python
License
—
Category
Last pushed
May 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/caixd-220529/LifelongAgentBench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
sierra-research/tau2-bench
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
xlang-ai/OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
bigcode-project/bigcodebench
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
THUDM/AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
scicode-bench/SciCode
A benchmark that challenges language models to code solutions for scientific problems