PaperGuru is the first memory primitive designed for long-horizon LLM agents, formalized as Lifecycle-Aware Memory (LAM) with four axioms.
- 66.05% on PaperBench, beating the best published baseline by 30.21%
- 94.66% content score on SurveyBench, 14.06% over prior work
- 10 peer-reviewed paper acceptances across FSE 2026, ICML 2026, TOSEM, AEI, and ICoGB
- Single algorithmic mechanism satisfying versioned content, multi-hop relevance, bounded query cost, and provenance-grounded composition