按年被提到
20262026 · 3 次2026
强化学习与智能体›大模型智能体·arXiv:2601.10825 · cs.CL

Reasoning Models Generate Societies of Thought

Junsol Kim, Shiyang Lai, Nino Scherrer, Blaise Agüera y Arcas, James Evans · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2026-01-22 · 最近 2026-02-12
3不同的人
2活跃月份
3讨论串
9被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks, attributed to extended computation through longer chains of thought. Here we show that enhanced reasoning emerges not from extended computation alone, but from simulating multi-agent-like interactions -- a society of thought -- which enables diversification and debate among internal cognitive perspectives characterized by distinct personality traits and domain expertise. Through quantitative analysis and mechanistic interpretability methods applied to reasoning traces, we find that reasoning models like DeepSeek-R1 and QwQ-32B exhibit much greater perspective diversity than instruction-tuned models, activating broader conflict between heterogeneous personality- and expertise-related features during reasoning. This multi-agent structure manifests in conversational behaviors, including question-answering, perspective shifts, and the reconciliation of conflicting views, and in socio-emotional roles that characterize sharp back-and-forth conversations, together accounting for the accuracy advantage in reasoning tasks. Controlled reinforcement learning experiments reveal that base models increase conversational behaviors when rewarded solely for reasoning accuracy, and fine-tuning models with conversational scaffolding accelerates reasoning improvement over base models. These findings indicate that the social organization of thought enables effective exploration of solution spaces. We suggest that reasoning models establish a computational parallel to collective intelligence in human groups, where diversity enables superior problem-solving when systematically structured, which suggests new opportunities for agent organization to harness the wisdom of crowds.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论chriddyp · 2026-02

“This is really cool. And timely! Check out the recent paper by Google et al re "Societies of Thought": https://arxiv.org/html/2601.10825v1. It goes into how different conversational behaviors (raising questions or just say "but wait..."), perspective shifts, conflict of perspectives, tension, tension release (jokes!), asking for opinions) and different pe…”

Show HN: agent alcove – Claude, GPT, and Gemini debate across forums原评论 ↗
被提交为 story · 2 次