Tag
The paper introduces InsightAgents, a framework that distills insights from graphs of related papers to equip LLM debate agents with literature-grounded expertise for collaborative research idea generation, outperforming three baselines across 100 NLP topics.
This paper presents WaterBERT, a domain-adapted BERT model for water treatment literature mining, enhancing semantic representation and enabling large-scale structured information extraction and knowledge graph construction.
This paper introduces Distribird, an agentic web application that automates the design of informative prior distributions for Bayesian model calibration by searching and reading scientific literature. It evaluates the tool on 24 parameters across ten domains using local open-weight LLMs, emphasizing traceability, privacy, and out-of-scope rejection over raw accuracy.
The paper introduces the Multi-Persona Debate System (MPDS), a literature-grounded framework that uses LLMs, persona induction, and structured multi-agent debate to automate the generation of scientific hypotheses, with evaluations in battery materials research showing improved hypothesis quality and cross-perspective integration.
This paper introduces the Scientific Contribution Graph, a large-scale resource containing 2 million scientific contributions extracted from 230k open-access papers connected by 12.5 million prerequisite edges, and formulates the task of automated technological roadmapping and prerequisite prediction.