Metraipolis › archive › dc_644cb9cc98dd
AffToM: Benchmarking Recursive Affective Theory of Mind in Dynamic Multi-Party Interactions — arXiv:2611.02725
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02725
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:53:44.013Z
- SHA-256 of the archived text
6c678331a3193a4eb9eedb7e0b7fe85f045657a98adcce48f87dc588fc797b48- Stable URL of this page
https://metraipolis.com/documento/dc_644cb9cc98dd
How to cite
AffToM: Benchmarking Recursive Affective Theory of Mind in Dynamic Multi-Party Interactions — arXiv:2611.02725 — arXiv (en), https://arxiv.org/abs/2611.02725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_644cb9cc98dd (Metraipolis archive dc_644cb9cc98dd, sha256 6c678331a3193a4eb9eedb7e0b7fe85f045657a98adcce48f87dc588fc797b48)
BibTeX
@misc{dc644cb9cc98dd,
title = {AffToM: Benchmarking Recursive Affective Theory of Mind in Dynamic Multi-Party Interactions — arXiv:2611.02725},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02725},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_644cb9cc98dd; sha256 6c678331a3193a4eb9eedb7e0b7fe85f045657a98adcce48f87dc588fc797b48},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding emotion in realistic social interactions requires more than recognizing facial expressions or assigning affective labels. The same event can elicit different emotions depending on what each participant knows, what they believe others know or feel, and how these nested mental states evolve over time. Existing benchmarks largely study higher-order epistemic Theory of Mind (ToM) and multimodal emotion reasoning in isolation, leaving recursive affective reasoning under asymmetric and dynamically changing information underexplored. Therefore, we introduce AffToM, a benchmark for affective ToM with 1,922 test pairs and 19,759 training pairs. AffToM evaluates Individual Affective Reasoning (IAR), which infers emotions from events and socio-cognitive context, and Multi-party Affective Reasoning (MPAR), which recursively tracks participants' nested beliefs and emotions as new evidence emerges. We develop an event-driven multi-agent generation pipeline grounded in dynamic character interaction graphs that explicitly capture event sequences, interpersonal relations, and mental-state updates. Furthermore, we propose AffToM-R1, a two-stage post-training framework combining supervised fine-tuning with perspective-aware rubric-guided reinforcement learning. Experiments show that MPAR remains challenging, with even the strongest evaluated MLLM achieving less than 60% accuracy, while AffToM-R1 improves MPAR accuracy by 13.38 percentage points over its base model. Our dataset is available at: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02725 — 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 2026-11-03T10:49:38.382Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).