Metraipolis › archive › dc_ec6aaa75aeeb

SocialBuddy: Tailoring Search Agent for Social Scenarios — arXiv:2609.01641

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01641
License (as archived): CC0-1.0
Archived: 2026-10-17T04:37:17.078Z
SHA-256 of the archived text: 093e768c9780226964e54a411893d6c938fbc614fb707b7f231b4a8cdf320ae7
Stable URL of this page: https://metraipolis.com/documento/dc_ec6aaa75aeeb

How to cite

SocialBuddy: Tailoring Search Agent for Social Scenarios — arXiv:2609.01641 — arXiv (en), https://arxiv.org/abs/2609.01641 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec6aaa75aeeb (Metraipolis archive dc_ec6aaa75aeeb, sha256 093e768c9780226964e54a411893d6c938fbc614fb707b7f231b4a8cdf320ae7)

BibTeX

@misc{dcec6aaa75aeeb,
  title = {SocialBuddy: Tailoring Search Agent for Social Scenarios — arXiv:2609.01641},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01641},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec6aaa75aeeb; sha256 093e768c9780226964e54a411893d6c938fbc614fb707b7f231b4a8cdf320ae7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01641. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In the era of digital social interaction, searching friends' posts from massive social streams has become a fundamental user need. However, while modern agentic search frameworks have achieved remarkable success in conventional retrieval tasks, they break down when confronted with heterogeneous user queries and multi-dimensional social feeds, resulting in severe performance degradation in complex social search. To bridge this gap, we introduce SocialBuddy, the first agentic search framework tailored for social scenarios. Specifically, we construct SocialEnv, the first large-scale simulated environment for social search. Powered by an automated data and trajectory synthesis pipeline, SocialEnv includes 200K user profiles, 10 million social posts, and 50K reasoning trajectories, establishing a solid foundation for the development of social search agents. To tackle the credit assignment dilemma caused by sparse rewards in social search, we design SocialPO, a hybrid-granularity optimization framework. It macroscopically reinforces successful reasoning paths via multi-dimensional rewards, while microscopically rectifying deviated trajectories through fine-grained prefix truncation and token-level supervision. This hybrid-granularity design delivers multi-scale guidance in complex long-sequence scenarios. Finally, we construct SocialSearch Benchmark to provide a quantitative evaluation scheme for assessing the social search capabilities of SocialBuddy. Extensive experiments demonstrate that SocialBuddy-35B surpasses significantly larger frontier LLMs. Code and dataset will be released upon article acceptance.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-03 in cs.SI).
Categorie arXiv: Social and Information Networks (cs.SI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.01641 — 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 2026-10-17T04:08:52.112Z dalla pagina https://arxiv.org/catchup/cs.SI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).