English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

RippleMem: Associative Memory for LLM Agents via Anchor-Based Ripple Diffusion

Forum topic · ✨步子哥 · 2026-08-14

Summary

RippleMem is a memory architecture for LLM agents that reframes long-term recall from retrieval (locate-and-return) to associative recollection (cue, diffuse, reassemble), inspired by Tulving's cue-dependent memory theory. It maintains cue-rich episodic units in an event-centric memory graph connected by semantic and structural links. At query time, hybrid semantic-structural anchoring locates initial memory anchors, after which an adaptive ripple diffusion expands outward over the graph to gather distributed evidence, which is then assembled into a coherent context for the LLM. On the LoCoMo benchmark, LLM-as-a-Judge accuracy improves by 3.95%, with large gains on evidence-scattered questions; on LongMemEval-S, accuracy rises by 11.87%, with the largest jumps on multi-hop queries. Graph construction is roughly 30x cheaper than prior graph-memory approaches because no full entity-relation graph is precomputed. Ablations confirm diffusion, not mixed retrieval, drives the gains. The work surfaces three design principles: organize memory rather than store it, diffuse rather than locate, and preserve rather than compress context.

Key points

  • Paradigm shift: Agent memory should be designed around *associative recollection* (cue–diffuse–reassemble), not flat *retrieval* (locate–and–return), grounded in Endel Tulving's cue-dependent recollection theory.
  • Three flaws in existing memory paradigms:
  • *Full-context*: bounded context windows and the "Lost in the Middle" effect.
  • *Flat retrieval (RAG)*: returns isolated similar records, not the multi-turn evidence chain needed by a query.
  • *Graph memory*: requires heavy upfront entity/relation extraction and compresses rich episodes into lean triples, losing time, place, and dialogue.
  • RippleMem architecture (four steps):
  • 1. *Memory graph construction*: each interaction becomes a cue-rich episodic memory unit preserving full context; units are linked by semantic and structural edges into an event-centric graph. 2. *Hybrid initial recollection*: mixed cues (semantic similarity + structural match) seed the top memory anchors. 3. *Anchor-localized diffusion*: ripples propagate adaptively along semantic and structural ties, depth and fan-out chosen per query (no full graph precomputed). 4. *Evidence reassembly*: gathered fragments are stitched into the LLM's prompt context.
  • Empirical results:
  • LoCoMo: +3.95% LLM-as-a-Judge accuracy, largest gains on evidence-scattered multi-hop items.
  • LongMemEval-S: +11.87% accuracy, largest gains on multi-hop queries.
  • Graph build cost ~30x lower than prior graph-memory methods.
  • Ablation: removing the diffusion module collapses performance, isolating diffusion—not hybrid retrieval—as the driver.
  • Why "ripple" beats "drawer"

  • Scattered evidence: A question like "张三's role in project X" may require linking a Monday meeting note, a Wednesday email, and a Friday conversation. Each item alone has low similarity to the query, so flat retrieval misses them; diffusion from a person-anchor pulls the chain together.
  • Context preservation: Episodic units retain time, place, people, and dialogue—RippleMem *organizes* memory rather than *compressing* it.
  • Adaptive scope: Simple queries use one anchor and a short ripple; complex queries trigger multi-hop, larger ripples.
  • Cognitive science anchor

    Tulving (1972) showed recall is *reconstruction*, not search: a word list is poorly recalled cold, but improves with one cue (e.g., "a fruit") and further with a sharper cue ("a red fruit"). RippleMem operationalizes this: anchors act as cues, the graph as the associative network, diffusion as the spreading activation, and reassembly as reconstruction.

    Cross-paper resonance

  • *Granularity isomorphism* (Heddle, CodeRescue): optimize at the same granularity as the target—RippleMem aligns memory structure granularity with the granularity of the recall process.
  • *Division over unification* (Euclid-MCP): let LLMs handle semantics while graph structures handle association—LLM understands; graph connects.
  • *Externalized memory*: joins a lineage from slime-mold traces and octopus RNA editing—memory organization is moved out of the LLM into an external structure that the model only reads.
  • Design principles for Agent memory

    1. Memory is organization, not storage. 2. Retrieval is diffusion, not pointwise lookup. 3. Context is preserved, not compressed into triples.

    Limitations and outlook

  • Validated on text only; multimodal, embodied, and tool-use memory are open.
  • LLM-mediated extraction, query analysis, and recall planning add latency and cost.
  • Existing benchmarks under-stress continuously growing personal memory.
  • Future work: multimodal episodes; caching/batching/async efficiency; long-horizon memory aging, evolution, and privacy deletion.
  • Links

  • Paper: https://arxiv.org/abs/2608.13334
  • Reproduction sketch (not an official repo): LangChain + Neo4j + an LLM API can implement the pipeline.

Bottom line

The contribution is not the 3.95% or 11.87% headline; it is the shift from *retrieval-as-database-with-search* to *memory-as-associative-network*. An agent whose memory ripples on a pond rather than sits in a drawer can reconstruct scattered evidence into coherent answers.

Tags

#llm-agents#long-term-memory#associative-recall#graph-memory#retrieval-augmented-generation#ripple-diffusion#cue-dependent-memory#agent-architecture

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633478