Shared Selective Persistent Memory for Agentic LLM Systems
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is token-inefficient and counterproductive: irrelevant context degrades generation quality. We introduce shared selective persistent memory, an architecture that identifies and retains four categories of reusable context (task specifications, data schemas, tool configurations, and o
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 67%NirDiamant/Agent_Memory_Techniques →
- PossiblePossibly related (embedding) · 63%joshuaswarren/remnic →
- PossiblePossibly related (embedding) · 62%LazyAGI/LazyLLM →
- PossiblePossibly related (embedding) · 29%thedotmack/claude-mem →
“Possibly related via embedding similarity 0.63 (not asserted). Timestamp check: artifact slightly before paper (-8d).”
- PossiblePossibly related (embedding) · 30%MemTensor/MemOS →
“Possibly related via embedding similarity 0.65 (not asserted). Timestamp check: artifact slightly before paper (-8d).”
- PossiblePossibly related (embedding) · 56%NovasPlace/CSM →
- LinkedLinked via arxiv author · 85%Sanjana Pedada →
“Shared Selective Persistent Memory for Agentic LLM Systems”
- LinkedLinked via arxiv author · 85%Aditya Dhavala →
“Shared Selective Persistent Memory for Agentic LLM Systems”