长视频记忆别手搓策略：Meta LVMH/SEEM，三基准均值 65.7%（+7.7 pp）、token ≈1/32

View PDF HTML (experimental)

Abstract:Long-video agents must map hours or days of multimodal evidence into a bounded context while respecting token and latency budgets, making memory design a context-management challenge. Existing memory systems largely rely on hand-designed policies, leaving open how to jointly optimize memory design for performance and efficiency. We propose Long Video Meta-memory Harness (LVMH), an automated multi-agent framework that formulates memory-policy development as multi-objective code search around a fixed answer model. To guard against self-certification and development-set overfitting, LVMH separates implementation from independent review and enforces protected observation boundaries. Persistent meta-memory records past proposals, traces, costs, and failures to guide subsequent policy revisions. Through this harness, we discover Self-Evolving Evidence Memory (SEEM), a "text-first, vision-second" policy that answers from compact structured event memory and evidence specialists, consulting localized frames through a selective visual gate. The policy evolved on EgoLifeQA generalizes to unseen benchmarks, outperforming Meta-Harness on both Ego-R1 Bench and Video-MME (L) with GPT-5 mini. Across the three benchmarks, SEEM with GPT-5 achieves 65.7% average accuracy, surpassing the previous state of the art by 7.7 percentage points with approximately 32x lower average evaluation token use and 91x shorter average response time.

Submission history

From: Liwei Che [view email]
[v1] Tue, 29 Sep 2026 20:29:13 UTC (517 KB)