StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Feb-17-2026, 23:01:39 GMT–Neural Information Processing Systems

To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence.

large language model, machine learning, natural language, (18 more...)

Neural Information Processing Systems

Feb-17-2026, 23:01:39 GMT

Conferences PDF

Country:
- Asia > Taiwan (0.04)

Genre:
- Research Report > New Finding (0.46)

Industry:
- Health & Medicine (0.47)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Neural Networks
    - Deep Learning (0.70)
  - Natural Language > Large Language Model (1.00)
  - Representation & Reasoning > Agents (1.00)

Duplicate Docs Excel Report

Title
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents

Similar Docs Excel Report more

Title	Similarity	Source
None found