Benchmark
UndoBench
What is UndoBench?
Tool-using AI agents are increasingly deployed across enterprise software systems, yet widely used benchmarks primarily evaluate nominal task completion…
- Released
- 2026-10-04
- Evaluates
- Agents & Tool Use, General AI, cs.SE
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- rule-auto-admitted
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2610.05622
UndoBench paper and code
No reported scores are on record for this benchmark yet.