Public KG record
AppWorld
Recorded overview
Simulated multi-app benchmark used to evaluate agentic memory systems.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: 用于评测 ReAct agent 的任务基准
- Benchmarks: 包含 168 个 test_normal 任务
- Benchmarks: 用于评测 ReAct agent 的重复运行一致性
- Benchmarks: 用于比较 JOLT+ 与 GRPO 的 state-test pass rate
Evidence coverage
The KG currently records 5 known information dimensions and has 12 undocumented dimensions, linked to 5 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- ALTK-Evolve — evaluated on
- ReAct agent — evaluated on
- agentic memory — evaluated on
- Arbitrary code execution — evaluated on
- JOLT — evaluated on