paper-with-me

홈 › Papers

Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base

2025-10-30 · Yu Li, Yuan Huang, Tao Wang, Caiyu Fan, Xiansheng Cai, Sihan Hu, Xinzijian Liu, Cheng Shi, Mingjun Xu, Zhen Wang, Yan Wang, Xiangqi Jin, Tianhan Zhang, Linfeng Zhang, Lei Wang, Youjin Deng, Pan Zhang, Weijie Sun, Xinyu Li, Weinan E, Linfeng Zhang, Zhiyuan Yao, Kun Chen arxiv

Most scientific materials compress reasoning, presenting conclusions while omitting the derivational chains that justify them. This compression hinders verification by lacking explicit, step-wise justifications and inhibits cross-domain links by collapsing the very pathways that establish the logical and causal connections between concepts. We introduce a scalable framework that decompresses scientific reasoning, constructing a verifiable Long Chain-of-Thought (LCoT) knowledge base and projecting it into an emergent encyclopedia, SciencePedia. Our pipeline operationalizes an endpoint-driven, reductionist strategy: a Socratic agent, guided by a curriculum of around 200 courses, generates approximately 3 million first-principles questions. To ensure high fidelity, multiple independent solver models generate LCoTs, which are then rigorously filtered by prompt sanitization and cross-model answer consensus, retaining only those with verifiable endpoints. This verified corpus powers the Brainstorm Search Engine, which performs inverse knowledge search -- retrieving diverse, first-principles derivations that culminate in a target concept. This engine, in turn, feeds the Plato synthesizer, which narrates these verified chains into coherent articles. The initial SciencePedia comprises approximately 200,000 fine-grained entries spanning mathematics, physics, chemistry, biology, engineering, and computation. In evaluations across six disciplines, Plato-synthesized articles (conditioned on retrieved LCoTs) exhibit substantially higher knowledge-point density and significantly lower factual error rates than an equally-prompted baseline without retrieval (as judged by an external LLM). Built on this verifiable LCoT knowledge base, this reasoning-centric approach enables trustworthy, cross-domain scientific synthesis at scale and establishes the foundation for an ever-expanding encyclopedia.

📄 PDF Abstract BibTeX arXiv:2510.26854

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representations

2025-08-31 · Albert Sadowski, Jarosław A. Chudziak arxiv

Legal reasoning requires both precise interpretation of statutory language and consistent application of complex rules, presenting significant challenges for AI systems. This paper introduces a modular multi-agent framew…

Natural Language UnderstandingLegal Reasoning

Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search

2025-11-24 · Manil Shrestha, Edward Kim arxiv

Multi-hop question answering over knowledge graphs remains computationally challenging due to the combinatorial explosion of possible reasoning paths. Recent approaches rely on expensive Large Language Model (LLM) infere…

Multi-hop Question AnsweringKnowledge DistillationAnswer GenerationKnowledge Graphs

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains

2026-05-18 · Zhonghang Yuan, Zhefan Wang, Fang Hu, Zihong Chen 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its app…

Reinforcement Learning

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

2026-08-19 · Zuocheng Ying, Yang Yang, Yumou Wu, Chuanbo Zhu 외 arxiv

Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods…

Question Answering

PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design

2026-05-26 · Manpreet Kaur, Xingying Zhang, Qian Liu arxiv

Polymer discovery is central to fields ranging from energy storage to biomedicine, but it is hindered by an astronomically large chemical design space and fragmented representations of structure, properties, and prior kn…

Representation Learning