This work proposes 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.
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.
Just-In-Time Agent Memory (JAM), a trainable framework for query-conditioned context construction at runtime, is proposed, where it achieves stronger task performance than AOT-style memory systems while remaining substantially more efficient than prior trained agentic memory approaches.
This work introduces a unified formulation of context optimization and shows that an agent memory system update can be interpreted as an optimization update procedure over the model's context, and proposes GraphMemory, a lightweight graph-based memory that accumulates, refines, organizes, and connects reusable strategi...
Yehya Farhat, Michael Desmond, Anastasios Kyrillidis· 0 citations
All-in-One Memory (AiO-Mem), which organizes these operations as transitions over a shared evidence state and directly evaluates the semantic quality of each action in a unified reward space, consistently improves answer accuracy over both static memory systems and RL-trained memory agents.
Bing-Bing Wang, Jing-Jie Lin, Wei-Ming Qiao et al.· 0 citations
MemAgent, featuring a content-aware routing architecture and a training-data synthesis pipeline, is proposed, featuring a content-aware routing architecture and a training-data synthesis pipeline that improves average accuracy and outperforms every individual memory method across all three benchmarks.
Yong-Xian Wei, Yi-Lin Zhao, Run-Xi Cheng et al.· 0 citations
InteraCtive Memory Learning is proposed, a multi-agent framework that transforms the memory mechanism from a passive archive into a learnable, interactive memory policy that significantly outperforms strong baselines.
Cai Ke, Jiang-Yue Yan, Han Zhang et al.· 1 citation
Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough to answer? We propose CASE, a plug-in termination framework that frames this decision as policy-conditioned sequential stopping. At each causal checkpoint, CASE combines...
Yi-Ming Du, Cheng-Hao Liu, Zhiyuan Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.