Metraipolis › archive › dc_955c8cb41968
Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings — arXiv:2610.32474
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32474
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:50:39.721Z
- SHA-256 of the archived text
eac036d122312c341442e76e2ffb8a5eff491894fe91b8c8f91ed568303dea6b- Stable URL of this page
https://metraipolis.com/documento/dc_955c8cb41968
How to cite
Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings — arXiv:2610.32474 — arXiv (en), https://arxiv.org/abs/2610.32474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_955c8cb41968 (Metraipolis archive dc_955c8cb41968, sha256 eac036d122312c341442e76e2ffb8a5eff491894fe91b8c8f91ed568303dea6b)
BibTeX
@misc{dc955c8cb41968,
title = {Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings — arXiv:2610.32474},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32474},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_955c8cb41968; sha256 eac036d122312c341442e76e2ffb8a5eff491894fe91b8c8f91ed568303dea6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Advances in Multimodal Large Language Models (MLLMs) have driven substantial progress in multimodal embeddings. Recent methods exploit generative capabilities by augmenting embedded inputs with self-generated reasoning to produce more informative embeddings. However, conventional retrieval supervision for training embedding models specifies pairwise relevance relations without explicitly guiding the reasoning used for input augmentation. Such reasoning is neither directly observed nor uniquely determined by the input, allowing multiple plausible traces to introduce semantic cues of varying retrieval utility. Existing approaches largely optimize reasoning conditioned on the input alone, limiting the exploration of retrieval-relevant traces. We introduce PILOT, a framework that models reasoning as a latent variable and instantiates its prior and posterior distributions as distinct reasoning modes of a shared MLLM. The prior conditions only on the input, whereas the posterior uses additional training-time relational evidence to guide reasoning exploration. To translate the posterior's broader exploration into inference-time improvements, we derive an importance-weighted variational objective and instantiate it as a prior-posterior co-evolution framework that improves both modes under a shared inference-compatible reward while selectively transferring posterior trajectories to the prior according to their utility and prior reachability. On the 78-task MMEB-V2 benchmark, PILOT outperforms the primary baseline across all 12 task groups at both 2B and 7B parameters, improving overall scores by 3.2 and 3.3 points, respectively, with the largest gains in visual-document retrieval (+6.1 and +6.4 points). Our results show that relational supervision is most valuable not as a post-hoc reward but as a signal for shaping how reasoning is explored in training reasoning-enhanced embedding models. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.32474 — 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 2026-10-26T19:45:33.318Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).