CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion
As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded memory interface. We study this evidence-reachability problem in long-term conversational memory, where retrieval still relies heavily on semantic similarity. This works well for topical recall, but it often misses earlier experiences, plans, or motivations that are semantically distant from the later events they help explain. Existing memory graphs provide cross-memory structure, yet links driven mainly by semantic ove
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) · 64%The biggest problem with AI memory isn't recall—it's stale facts [P] →
- PossiblePossibly related (embedding) · 60%TRACE: open-source hierarchical memory for LLM agents, 82.5% on MemoryAgentBench’s EventQA using gpt-oss-20B [P] →
- PossiblePossibly related (embedding) · 60%Evaluating long-term memory limits in stateless LLM chatbots — feedback needed [D] →
- LinkedLinked via arxiv author · 85%Zheling Tan →
“CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion”
- LinkedLinked via arxiv author · 85%Jin Gao →
“CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion”
- LinkedLinked via arxiv author · 85%Dequan Wang →
“CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”