Benchmarks
MemoryAgentBench
ICLR 2026; incremental multi-turn evaluation; the only one with a reproducible public harness
Benchmark
★ 486 on GitHub · last commit Sep 25, 2026
What it is
ICLR 2026; incremental multi-turn evaluation; the only one with a reproducible public harness
At a glance
- Business model
- Benchmark
- License
- MIT
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions” (repository description)
- Stars
- 486
- Forks
- 63
- Open issues
- 6
- Last commit
- Sep 25, 2026 (46 days ago)
- License (GitHub)
- MIT
Links and sources
- Official sitearxiv.org/abs/2507.05257
- GitHub repositorygithub.com/HUST-AI-HYZ/MemoryAgentBench
Added nov 8, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.