The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, determine the outcome of the whole run. Making these decisions well is becoming a key capability for both engineering and research agents. We refer to the ability to make good long-horizon decisions as the taste of an agent. While existing benchmarks measure the end-to-end success of agents on long-horizon tasks, none of them measures the taste of an agent. To address this problem, we build Taste-Bench, a benchmark of taste questions constructed automatically from trajectories that agents produced in engineering and research t...
| Authors | Wenbo Pan, Zhichao Liu, Shujie Liu et al. |
|---|---|
| Primary category | cs.AI |
| Published | 22 September 2026 |
| Last updated at source | 23 September 2026 |
Connected in the knowledge graph
- wenbopan/taste-benchDataset · cited by
Models and datasets referencing this paper
- wenbopan/taste-benchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.