Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

ShardMemo: Scope-Before-Routing for Agentic Memory Retrieval

Yang Zhao, Chengxiao Dai, Mengying Kou, Yue Xiu +1 more

Published

Jan 29, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 31, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
5/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget. Existing memory systems handle access scope in two flawed ways: applying scope after retrieval wastes probe budget on inadmissible memories, while treating scope as a learned ranking feature makes a hard constraint depend on router quality. We present SHARD-MEMO, an agentic memory system built on scope-before-routing: metadata predicates first identify the admissible shards, and a learned router then selects a small number of them for shard-local approximate nearest neighbor retrieval. Given the supplied scope predicate and metadata, this separates hard admissibility from learned relevance ranking, so inadmissible shards cannot consume shard-probe budget. We evaluate on LoCoMo, HotpotQA, and ToolBench, covering conversational, long-context, and procedural memory. Under matched supervision and fixed budgets, SHARDMEMO improves over a learned router baseline by roughly +3 F1 on LoCoMo; in end-to-end LoCoMo evaluation it improves over the strongest evaluated memory baseline by up to +6.8 F1, with gains on HotpotQA and ToolBench.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget."

Benchmarks / Datasets

partial

ToolBench, HotpotQA

Useful for quick benchmark comparison.

"We evaluate on LoCoMo, HotpotQA, and ToolBench, covering conversational, long-context, and procedural memory."

Reported Metrics

partial

F1, Relevance

Useful for evaluation criteria comparison.

"Given the supplied scope predicate and metadata, this separates hard admissibility from learned relevance ranking, so inadmissible shards cannot consume shard-probe budget."

Benchmarks and datasets

ToolBenchHotpotQA

Reported metrics

f1relevance
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Ranking (inferred)
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constraints: which memories it is permitted to access, and which are relevant under a limited search budget.
  • Existing memory systems handle access scope in two flawed ways: applying scope after retrieval wastes probe budget on inadmissible memories, while treating scope as a learned ranking feature makes a hard constraint depend on router quality.
  • We present SHARD-MEMO, an agentic memory system built on scope-before-routing: metadata predicates first identify the admissible shards, and a learned router then selects a small number of them for shard-local approximate nearest neighbor retrieval.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

F1

Contribution summary

  • We present SHARD-MEMO, an agentic memory system built on scope-before-routing: metadata predicates first identify the admissible shards, and a learned router then selects a small number of them for shard-local approximate nearest neighbor…
  • We evaluate on LoCoMo, HotpotQA, and ToolBench, covering conversational, long-context, and procedural memory.
  • Under matched supervision and fixed budgets, SHARDMEMO improves over a learned router baseline by roughly +3 F1 on LoCoMo; in end-to-end LoCoMo evaluation it improves over the strongest evaluated memory baseline by up to +6.8 F1, with gains…

Why it matters for eval

  • We present SHARD-MEMO, an agentic memory system built on scope-before-routing: metadata predicates first identify the admissible shards, and a learned router then selects a small number of them for shard-local approximate nearest neighbor…
  • Under matched supervision and fixed budgets, SHARDMEMO improves over a learned router baseline by roughly +3 F1 on LoCoMo; in end-to-end LoCoMo evaluation it improves over the strongest evaluated memory baseline by up to +6.8 F1, with gains…

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: ToolBench, HotpotQA

  • Metric reporting is present

    Detected: f1, relevance