SocialBuddy framework enhances social media search capabilities

Researchers have introduced SocialBuddy, a novel agentic search framework designed specifically for complex social media scenarios. To support its development, they created SocialEnv, a large-scale simulated environment containing user profiles and social posts, along with a benchmark for evaluating social search capabilities. SocialBuddy utilizes a hybrid-granularity optimization framework called SocialPO to address sparse rewards by reinforcing successful reasoning paths and rectifying deviations. Experiments indicate that SocialBuddy-35B outperforms larger frontier LLMs in social search tasks. AI

IMPACT This framework could significantly improve user experience and information retrieval within social media platforms.

RANK_REASON The cluster contains a research paper detailing a new AI framework and dataset for social search. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• ScienceCast
• SocialBuddy-35B
• SocialEnv
• SocialPO
• SocialSearch Benchmark

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →