Agent Memory Leaderboard Releases Public Evaluation Code with Multiple Datasets
rohanpaul_ai · x · 2026-08-07
The Agent Memory Leaderboard has released public evaluation code covering datasets like beam, clbench, locomo-refined, longmemeval-s, personamem, and scriptmem. Requires Python 3.10+, API config via CLI or env vars. Disclosed runtime behavior includes concurrency, timeouts, retries, key rotation, checkpoints, and aggregation. Production parameters: 72-hour timeout, topk 100.
Related event: 20+ Institutions Launch Agent Memory Leaderboard (AML)(5 posts)→
More from Research
- A beginner-friendly introduction to causal inference kicks off, Part 1 — Nasereliver · 2026-10-16
- FBI method trains for Pass@K with one sample per update at 12.3% of the cost — EmtiyazKhan · 2026-10-16
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16