Metraipolis › archive › dc_4ad549163ffc
An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation — arXiv:2610.31685
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31685
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:50:51.674Z
- SHA-256 of the archived text
e5d554e4704cb736487583145724f1adad2a93f80c74f88d6d4ca168037d42fa- Stable URL of this page
https://metraipolis.com/documento/dc_4ad549163ffc
How to cite
An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation — arXiv:2610.31685 — arXiv (en), https://arxiv.org/abs/2610.31685 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ad549163ffc (Metraipolis archive dc_4ad549163ffc, sha256 e5d554e4704cb736487583145724f1adad2a93f80c74f88d6d4ca168037d42fa)
BibTeX
@misc{dc4ad549163ffc,
title = {An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation — arXiv:2610.31685},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31685},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ad549163ffc; sha256 e5d554e4704cb736487583145724f1adad2a93f80c74f88d6d4ca168037d42fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31685. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-based multimodal emotion reasoning systems perform well on standard benchmarks, but improving them through instruction tuning can be computationally expensive. Agentic pipelines built from frozen models avoid this cost, but introduce a different challenge: when a prediction is wrong, the system must identify which agent or stage caused the error. We address this problem with an agentic framework for traceable multimodal emotion reasoning and prompt-space adaptation. Modality-specific perception agents analyze visual, acoustic, and lexical inputs and post evidence-cited observations to a shared board. An integration agent combines these observations with retrieved multimodal examples to produce an emotion description, label set, and supporting citations, while an MLLM critic can request one revision before the output is finalized. For incorrect predictions, a separate evidence-grounded verification stage applies deterministic checks to verify that cited evidence and references are valid, and an entailment check to determine whether the final claims are supported by that evidence. Detected failures are then grouped by the responsible component and failure type, converted into targeted prompt patches, and accepted only after validation on a held-out set. This adapts the agent prompts without updating model weights. On the MER2025 dataset, targeted prompt adaptation outperforms the frozen static pipeline on all four MLLMs, ranging from 2B to 38B parameters, and matches or outperforms undifferentiated reflection baselines on each of them: VideoLLaMA3-2B, Phi-3.5-vision-instruct, Qwen2.5-VL-7B-Instruct, and InternVL2.5-38B. It improves F-score by 0.6--2.2 points depending on the backbone, including an increase from 52.3 to 54.5 on Qwen2.5-VL-7B. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Multimedia (cs.MM); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2610.31685 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-26T19:45:33.344Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).