Python · MIT
mohammadtavakoli78/BEAM
[ICLR 2026] Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
★ 167
Stars
17 forks · 15 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
15.9
Momentum / 100
see the breakdown below
12mo ago
Created
last push 2mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 9.5 | last push 2mo ago; decays to zero at 180 days |
| Scale | 15 | 6.5 | 167 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 15.9 | capped at 35 because growth is unmeasured |
Detail
| Topics | beambeam-benchmarkbenchmark-long-contextbenchmark-long-term-memorybenchmarkinglightlight-frameworkllmlong-context-evaluationlong-context-evaluation-benchmarklong-context-llmlong-context-llmslong-term-memorylong-term-memory-benchmarklong-term-memory-methodmachine-learningnatural-language-processingnlpragretrieval-augmented-generation |
| Matched on | RAG (retrieval-augmented-generation) |
| Short window | +0 stars over 9 days = 0.0/day |
| Long window | +12 stars over 26 days = 0.5/day |
| Lifetime average | 0.45 stars/day over 373 days |
| First seen here | 2026-10-11 |
| Last read | 11d ago |