# Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences

arXiv: https://arxiv.org/abs/2609.27175 · HTML: https://mlsanity.com/paper/2609.27175/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 62 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models](https://mlsanity.com/paper/2205.12487/) (2022)
- [Symbolic Learning Enables Self-Evolving Agents](https://mlsanity.com/paper/2406.18532/) (2024)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization](https://mlsanity.com/paper/2402.17574/) (2024)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models](https://mlsanity.com/paper/2002.06652/) (2020)
- [VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought](https://mlsanity.com/paper/2406.14596/) (2024)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [Contextual Experience Replay for Self-Improvement of Language Agents](https://mlsanity.com/paper/2506.06698/) (2025)
- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [Argumentative Large Language Models for Explainable and Contestable Claim Verification](https://mlsanity.com/paper/2405.02079/) (2024)
- [EmbraceNet: A robust deep learning architecture for multimodal classification](https://mlsanity.com/paper/1904.09078/) (2019)
- [Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence](https://mlsanity.com/paper/2604.24954/) (2026)
- [Interactive Explanations by Conflict Resolution via Argumentative Exchanges](https://mlsanity.com/paper/2303.15022/) (2023)
- [Useful Memories Become Faulty When Continuously Updated by LLMs](https://mlsanity.com/paper/2605.12978/) (2026)
- [MetaReflection: Learning Instructions for Language Agents using Past Reflections](https://mlsanity.com/paper/2405.13009/) (2024)
- [RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection](https://mlsanity.com/paper/2311.09939/) (2023)
- [Cheap-fake Detection with LLM using Prompt Engineering](https://mlsanity.com/paper/2306.02776/) (2023)
- [Contestable AI needs Computational Argumentation](https://mlsanity.com/paper/2405.10729/) (2024)
- [ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation](https://mlsanity.com/paper/2508.20131/) (2025)
- [RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents](https://mlsanity.com/paper/2605.16045/) (2026)
- [Multimedia Verification Through Multi-Agent Deep Research Multimodal Large Language Models](https://mlsanity.com/paper/2507.04410/) (2025)
- [Argumentation for Explainable and Globally Contestable Decision Support with LLMs](https://mlsanity.com/paper/2603.14643/) (2026)
- [Fact-Checking at Scale: Multimodal AI for Authenticity and Context Verification in Online Media](https://mlsanity.com/paper/2508.08592/) (2025)

## Abstract (arXiv)

Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.