English

StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Computation and Language 2024-11-01 v2

Abstract

Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capabilities and do not assess their ability to improve over time. To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence. StreamBench simulates an online learning environment where LLMs receive a continuous flow of feedback stream and iteratively enhance their performance. In addition, we propose several simple yet effective baselines for improving LLMs on StreamBench, and provide a comprehensive analysis to identify critical components that contribute to successful streaming strategies. Our work serves as a stepping stone towards developing effective online learning strategies for LLMs, paving the way for more adaptive AI systems in streaming scenarios. Source code: https://github.com/stream-bench/stream-bench. Benchmark website: https://stream-bench.github.io.

Keywords

Cite

@article{arxiv.2406.08747,
  title  = {StreamBench: Towards Benchmarking Continuous Improvement of Language Agents},
  author = {Cheng-Kuang Wu and Zhi Rui Tam and Chieh-Yen Lin and Yun-Nung Chen and Hung-yi Lee},
  journal= {arXiv preprint arXiv:2406.08747},
  year   = {2024}
}

Comments

NeurIPS 2024 Track on Datasets and Benchmarks

R2 v1 2026-06-28T17:03:58.307Z