ECHO：面向长程智能体的可审计双路径记忆系统

View PDF HTML (experimental)

Abstract:Long-horizon agents require more than retrieval over stored conversations: they must preserve source evidence, revise outdated knowledge, and distinguish relevant memories from sufficient support for an answer. We present ECHO (Embodied Context & History Orchestration), an auditable dual-path memory system. A fast path captures immutable events and serves multi-route recall, while asynchronous workers consolidate experience into revisable state and rebuild derived indexes. Source provenance, temporal authority, and answer realization are explicit boundaries. The service supports original-source packets with evidence-use checks and disables model-based reranking by default. For the latest reported accuracy, the authors confirm mixed retrieved inputs comprising original dialogue and memory summaries, answered by Qwen3-8B with NF4 quantization. In the latest author-supplied five-system aggregate evaluation, ECHO reports 56.27% answer accuracy, 98.04% source Hit@10, 93.58% macro source Recall@5, and 13.92% hallucination flags, with 19.54 ms mean retrieval latency. Its reported accuracy exceeds Mem0 by 4.53 percentage points in this snapshot. The results are descriptive aggregates; matched question-level evaluation and generation latency remain to be established. We separate these observations from earlier published experiments and engineering regressions.

Comments:	8 pages. Revised title and dual-path architecture; updated five-system aggregate evaluation and clarified reader configuration, evidence scope, and limitations
Subjects:	Artificial Intelligence (cs.AI)
Cite as:	arXiv:2608.21755 [cs.AI]
	(or arXiv:2608.21755v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2608.21755 arXiv-issued DOI via DataCite

Submission history

From: Boyang Guo [view email]
[v1] Sat, 22 Aug 2026 03:33:24 UTC (26 KB)
[v2] Tue, 20 Oct 2026 02:23:30 UTC (21 KB)