Ai agents: LoCoMo accuracy is the shared direct-receipt signal

Selected angle: source

One-sentence thesis

Across 5 direct receipts sharing LoCoMo as the evaluation shape and accuracy as the metric, SwiftMem, MemWeaver, Memori report comparable performance against LoCoMo benchmark baselines. Reported values include 47score, 95%, 81.95%, 93.3%, 70.4%.

Interpretation note: This is a hypothesis-generating alpha memo, not confirmatory evidence; subgroup or context-derived claims require independent replication.

Why this is surprising

The signal is bounded to LoCoMo accuracy: the receipts are comparable because they share the benchmark/task/metric shape, even though individual systems may differ.

Evidence Landscape

Bounded research question: Do independent direct receipts on LoCoMo continue to support a signal on accuracy for the cited systems when comparators are kept explicit?

Evidence receipts

• fact_id=210507 (A_core) — Experiments on LoCoMo and LongMemEval benchmarks demonstrate that SwiftMem achieves 47$\times$ faster search compared to state-of-the-art baselines while maintaining competitive accuracy, enabling practical deployment of memory-augmented LL doi=10.48550/arxiv.2601.08160
• fact_id=210432 (A_core) — Experiments on the LoCoMo benchmark demonstrate that MemWeaver substantially improves multi-hop and temporal reasoning accuracy while reducing input context length by over 95% compared to long-context baselines. doi=10.48550/arxiv.2601.18204
• fact_id=207489 (A_core) — Evaluated on the LoCoMo benchmark, Memori achieves 81.95% accuracy, outperforming existing memory systems while using only 1,294 tokens per query (~5% of full context). source=Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agents
• fact_id=207205 (A_core) — On LoCoMo-Plus, a Level-2 cognitive memory benchmark testing implicit constraint recall, Kumiho achieves 93.3% judge accuracy (n=401); independent reproduction by the benchmark authors yielded results in the mid-80% range, still substantial source=Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures
• fact_id=333530 (A_core) — V3.3 achieves 70.4% on LoCoMo in Mode A (zero-LLM). doi=10.5281/zenodo.19435120

What this changes

Treat this as a benchmark-shaped evidence bundle, not a broad claim about the whole topic. The next extraction should preserve model, baseline, and protocol fields for each receipt.

Limitations

• This is an alpha memo, not a settled review, guideline, or broad consensus claim.
• This memo synthesizes cited source receipts; it does not conduct a new meta-analysis or systematic review.
• Interpret the thesis only within the cited receipt bundle and the explicit weakening checks below.
• Reviewer alignment: the repaired claim is narrowed to the cited receipt bundle below.
• Independent receipts fail to reproduce the claimed contrast.
• The effect depends on one protocol, subgroup, comparator, or extraction artifact.

What would weaken this

• Independent receipts fail to reproduce the claimed contrast.
• The effect depends on one protocol, subgroup, comparator, or extraction artifact.

Strongest counter-evidence

• No direct opposing receipt was selected by this run. Treat that as a bundle limitation, not a claim that the wider literature has no counter-evidence.