Problem
PRISM (Pareto-Efficient Retrieval over Intent-Aware Structured Memory, arXiv:2605.12260, May 2026) is a training-free, retrieval-side framework that occupies a previously empty corner of the accuracy-vs-context-cost frontier. While SimpleMem (covered 08-05) optimizes the ingestion side, PRISM optimizes retrieval: it formulates memory retrieval as a min-cost selection problem over a graph-structured memory store.
Four orthogonal modules:
- Hierarchical bundle search over typed relation paths — retrieves related fact clusters, not isolated facts.
- Query-sensitive edge-cost adjustment — edges between facts have costs that shift based on query intent.
- Evidence compression — an LLM-side step that compresses retrieved evidence before injecting into context.
- Adaptive intent routing — classifies query complexity and adjusts retrieval scope without a per-query LLM call (unlike SimpleMem's intent-aware retrieval which requires LLM inference per query).
On LoCoMo, PRISM achieves strong accuracy at an order-of-magnitude smaller context budget than full-context baselines, outperforming Mem0, Mem0g, and MAGMA under equal-protocol comparisons.
Why it matters for Hermes
tqmemory's retrieval is currently semantic-search-based (embedding similarity). As the note store grows (the evolution pipeline generates notes every cycle), retrieval quality degrades — more results returned, more noise, higher context cost. PRISM's approach of building typed relation paths over the existing link_entities graph and using min-cost path selection would improve retrieval precision without requiring changes to how notes are written.
The adaptive intent routing (no per-query LLM call) is especially attractive for cost-sensitive autonomous workflows — it avoids the token overhead of SimpleMem's LLM-based intent inference. The evidence compression step directly addresses the context-budget problem: retrieved memories are compressed before injection, reducing token consumption.
Proposed Solution
- Graph-based retrieval mode. Add alongside existing semantic search: build typed relation paths over existing entity links (references, related-to, supersedes).
- Complexity classification. For each query, classify complexity (simple lookup vs. multi-hop reasoning) using lightweight heuristics — no LLM call needed.
- Min-cost path traversal. For complex queries, traverse the relation graph with min-cost path selection, bundling related notes.
- Evidence compression. Compress retrieved evidence via a short LLM summarization pass before injecting into agent context.
This is a retrieval-side complement to any ingestion-side compression (SimpleMem-style) and uses infrastructure tqmemory already has (the entity graph from link_entities).
Acceptance Criteria
Source
Priority
Priority score: 0.72 (Impact Medium × Effort Medium). Training-free and uses infrastructure tqmemory already has (entity graph). Retrieval-side optimization that complements ingestion-side approaches.
Dedup note
Distinct from #1713 (Multi-strategy retrieval — BM25 + temporal + cross-encoder reranking). #1713 adds more retrieval strategies (lexical, temporal, reranking fusion). PRISM optimizes retrieval path selection over the graph (min-cost traversal of typed relation edges, bundle search, query-sensitive edge costs, evidence compression). They operate at different layers: #1713 is about which similarity signals to fuse; PRISM is about how to traverse the relation graph optimally. Complementary, not overlapping — #1713 could feed candidates to PRISM's graph traversal.
Problem
PRISM (Pareto-Efficient Retrieval over Intent-Aware Structured Memory, arXiv:2605.12260, May 2026) is a training-free, retrieval-side framework that occupies a previously empty corner of the accuracy-vs-context-cost frontier. While SimpleMem (covered 08-05) optimizes the ingestion side, PRISM optimizes retrieval: it formulates memory retrieval as a min-cost selection problem over a graph-structured memory store.
Four orthogonal modules:
On LoCoMo, PRISM achieves strong accuracy at an order-of-magnitude smaller context budget than full-context baselines, outperforming Mem0, Mem0g, and MAGMA under equal-protocol comparisons.
Why it matters for Hermes
tqmemory's retrieval is currently semantic-search-based (embedding similarity). As the note store grows (the evolution pipeline generates notes every cycle), retrieval quality degrades — more results returned, more noise, higher context cost. PRISM's approach of building typed relation paths over the existing
link_entitiesgraph and using min-cost path selection would improve retrieval precision without requiring changes to how notes are written.The adaptive intent routing (no per-query LLM call) is especially attractive for cost-sensitive autonomous workflows — it avoids the token overhead of SimpleMem's LLM-based intent inference. The evidence compression step directly addresses the context-budget problem: retrieved memories are compressed before injection, reducing token consumption.
Proposed Solution
This is a retrieval-side complement to any ingestion-side compression (SimpleMem-style) and uses infrastructure tqmemory already has (the entity graph from
link_entities).Acceptance Criteria
Source
2026-08-06.md, finding chore(actions)(deps): bump marocchino/sticky-pull-request-comment from 2.9.1 to 3.0.4 #3: PRISM: Pareto-Efficient Graph-Based Retrieval.Priority
Priority score: 0.72 (Impact Medium × Effort Medium). Training-free and uses infrastructure tqmemory already has (entity graph). Retrieval-side optimization that complements ingestion-side approaches.
Dedup note
Distinct from #1713 (Multi-strategy retrieval — BM25 + temporal + cross-encoder reranking). #1713 adds more retrieval strategies (lexical, temporal, reranking fusion). PRISM optimizes retrieval path selection over the graph (min-cost traversal of typed relation edges, bundle search, query-sensitive edge costs, evidence compression). They operate at different layers: #1713 is about which similarity signals to fuse; PRISM is about how to traverse the relation graph optimally. Complementary, not overlapping — #1713 could feed candidates to PRISM's graph traversal.