# IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory

arXiv: https://arxiv.org/abs/2604.20136 · HTML: https://mlsanity.com/paper/2604.20136/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 30 of 37)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [Action Genome: Actions as Composition of Spatio-temporal Scene Graphs](https://mlsanity.com/paper/1912.06992/) (2019)
- [Scene Graph Generation from Objects, Phrases and Region Captions](https://mlsanity.com/paper/1707.09700/) (2017)
- [AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning](https://mlsanity.com/paper/2103.16002/) (2021)
- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [Explainable and Explicit Visual Reasoning over Scene Graphs](https://mlsanity.com/paper/1812.01855/) (2018)
- [Spatial-Temporal Transformer for Dynamic Scene Graph Generation](https://mlsanity.com/paper/2107.12309/) (2021)
- [Learning to Generate Scene Graph from Natural Language Supervision](https://mlsanity.com/paper/2109.02227/) (2021)
- [Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning](https://mlsanity.com/paper/2210.06031/) (2022)
- [Language-Conditioned Graph Networks for Relational Reasoning](https://mlsanity.com/paper/1905.04405/) (2019)
- [From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models](https://mlsanity.com/paper/2404.00906/) (2024)
- [Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation](https://mlsanity.com/paper/2210.12649/) (2022)
- [Unbiased Scene Graph Generation in Videos](https://mlsanity.com/paper/2304.00733/) (2023)
- [Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation](https://mlsanity.com/paper/2103.05271/) (2021)
- [Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning](https://mlsanity.com/paper/2412.08614/) (2024)
- [ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives](https://mlsanity.com/paper/2411.19083/) (2024)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [OED: Towards One-stage End-to-End Dynamic Scene Graph Generation](https://mlsanity.com/paper/2405.16925/) (2024)
- [EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2508.10729/) (2025)
- [Learning the What and How of Annotation in Video Object Segmentation](https://mlsanity.com/paper/2311.04414/) (2023)
- [Navigating Open Set Scenarios for Skeleton-based Action Recognition](https://mlsanity.com/paper/2312.06330/) (2023)
- [Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments](https://mlsanity.com/paper/2307.07757/) (2023)
- [Universal Scene Graph Generation](https://mlsanity.com/paper/2503.15005/) (2025)
- [Fine-Grained Captioning of Long Videos through Scene Graph Consolidation](https://mlsanity.com/paper/2502.16427/) (2025)
- [MICA: Multi-Agent Industrial Coordination Assistant](https://mlsanity.com/paper/2509.15237/) (2025)

## Built on by (most cited first, 2 of 2)

- [Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning](https://mlsanity.com/paper/2606.17591/) (2026)
- [A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory](https://mlsanity.com/paper/2609.30813/) (2026)

## Abstract (arXiv)

Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection, forcing annotators to revisit raw video and reconstruct temporal logic from scratch. The core bottleneck is not generation quality alone, but the absence of a supervisory interface through which human effort can be proportional to the scope of each error. We present IMPACT-CYCLE, a supervisory multi-agent system that reformulates long-video understanding as iterative claim-level maintenance of a shared semantic memory -- a structured, versioned state encoding typed claims, a claim dependency graph, and a provenance log. Role-specialized agents operating under explicit authority contracts decompose verification into local object-relation correctness, cross-temporal consistency, and global semantic coherence, with corrections confined to structurally dependent claims. When automated evidence is insufficient, the system escalates to human arbitration as the supervisory authority with final override rights; dependency-closure re-verification then ensures correction cost remains proportional to error scope. Experiments on VidOR show substantially improved downstream reasoning (VQA: 0.71 to 0.79) and a 4.8x reduction in human arbitration cost, with workload significantly lower than manual annotation. Code will be released at https://github.com/MKong17/IMPACT_CYCLE.