PRO-LONG — tool profile and history

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

Active

Canonical source ↗

Language
Python
Created
Last activity
Topics
  • agent-memory
  • arc-agi
  • llm-agents
  • long-horizon

Current measurement

341GitHub stars—
estimated momentum

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
341GitHub stars

Classifications

Domains
Type
Other
Use cases
  • No declared use case

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.