English(EN) Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning

LLM通过显式的if-then规则改进心智理论推理 · 跟踪1个来源

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了一种方法，通过生成显式的if-then规则来连接感知、信念和行动，从而提高大型语言模型的心智理论（ToM）推理能力。他们使用组相对策略优化（GRPO）在ToM基准测试上训练了Qwen2.5和Llama 3等模型，发现这种基于规则的方法优于提示和监督微调等其他方法。此外，由大型模型生成的规则展示了可迁移的知识，增强了GPT-4o mini等小型模型的性能。 AI

影响这项研究可能促使LLM更好地理解和预测人类行为，从而改进人机交互和个性化AI助手等领域的应用。

排序理由该集群包含一篇学术论文，详细介绍了提高LLM推理能力的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 18 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了提高LLM推理能力的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings, Paulina Hussein, Mehwish Alam, Vera Demberg · 2026-10-15 04:00

通过强化学习学习感知到行动的规则以进行心智理论推理

arXiv:2610.19796v1 Announce Type: cross Abstract: In Theory-of-Mind (ToM) reasoning, large language models may correctly infer the agent's mental state but fail to use that inference when predicting or judging the agent's subsequent actions. In this work, we investigate whether e…

本文如何被排名

报道来源 [1]

通过强化学习学习感知到行动的规则以进行心智理论推理

相关实体

相关话题