Metraipolis › archive › dc_4baba842597a
MM-ContextFold: Context Folding for Multimodal Agentic Retrieval — arXiv:2609.23121
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23121
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:58:52.878Z
- SHA-256 of the archived text
06701f39af7724fa5aaa7996322a64e09dbfe2861a6c1ca6dbc7b971a73d0a3c- Stable URL of this page
https://metraipolis.com/documento/dc_4baba842597a
How to cite
MM-ContextFold: Context Folding for Multimodal Agentic Retrieval — arXiv:2609.23121 — arXiv (en), https://arxiv.org/abs/2609.23121 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4baba842597a (Metraipolis archive dc_4baba842597a, sha256 06701f39af7724fa5aaa7996322a64e09dbfe2861a6c1ca6dbc7b971a73d0a3c)
BibTeX
@misc{dc4baba842597a,
title = {MM-ContextFold: Context Folding for Multimodal Agentic Retrieval — arXiv:2609.23121},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23121},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4baba842597a; sha256 06701f39af7724fa5aaa7996322a64e09dbfe2861a6c1ca6dbc7b971a73d0a3c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23121. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal Agentic Retrieval (MAR) requires agents to solve complex information-seeking tasks by iteratively invoking external tools. Typical frameworks such as ReAct maintain raw multimodal inputs and the accumulating interaction history in a single, ever-growing context, leading to the context explosion problem. While existing methods alleviate this issue by compressing redundant text, effective strategies for managing token-intensive visual content remain largely underexplored. To address this gap, we first conduct a systematic empirical study of approximately 10,000 trajectories. The results show that as visual cues are progressively extracted through external tools and textualized into the context, raw images become increasingly redundant. Continued image retention is associated with higher output entropy and can even degrade task accuracy. Motivated by these findings, we propose MM-ContextFold, a training-free framework that loads raw images only when needed. It maintains a persistent, text-only main context for high-level planning and spawns ephemeral branch contexts for image-dependent subtasks. Within each branch, the agent loads the relevant images, completes the subtask, and folds the result back into the main context as a concise textual summary; the images and branch trace are then discarded. Experiments on seven MAR benchmarks across five backbone models show that MM-ContextFold improves average accuracy by 6.3 percentage points over ReAct while reducing the working context length by 27.5\%. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.IR). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2609.23121 — 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 2026-10-09T21:45:02.236Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).