CogniRoute: Learning to Route Social Evidence in Omni-Modal Models

• 类型：arxiv
• 标识：2606.20970
• 链接：https://arxiv.org/abs/2606.20970
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar + OpenAlex
• S2被引：0
• OpenAlex被引：0
• 影响力被引：0
• TLDR：CogniRoute, a schema-guided Mixture-of-Experts framework for social omni reasoning, is introduced and route-aware reinforcement learning is introduced, which jointly optimizes token generation and expert allocation using rewards for answer correctness, modality-consistent reasoning, and cognitive temporal grounding.
• OpenAlex ID：W7165688957
• OpenAlex DOI：10.48550/arxiv.2606.20970
• DOI：10.48550/arxiv.2606.20970
• DOI来源：OpenAlex
• 开放获取：green
• 开放获取链接：https://doi.org/10.48550/arxiv.2606.20970
• OpenAlex更新：2026-07-19
• 待LLM分类：否
• 标题中文：CogniRoute：全模态模型中的社交证据路由学习
• TLDR中文：提出 CogniRoute，一种面向社交全模态推理的 schema 引导 Mixture-of-Experts（混合专家）框架，并引入路由感知强化学习，通过答案正确性、模态一致性推理与认知时序锚定等奖励联合优化 token 生成与专家分配。
• 来源文件：
• /inbox/tom/_candidates/2026-06-30-rag-retrieval-reranking-candidates.json
• [S2 enrich]
• [OpenAlex backfill]