The field of human-AI collaboration in research is moving towards a more integrated and interactive approach, with a focus on developing systems that can facilitate effective communication and knowledge sharing between humans and AI agents. Recent developments have highlighted the potential of large language models (LLMs) in advancing scientific discovery and interdisciplinary research, with applications in areas such as physics, linguistics, and disaster informatics. Noteworthy papers in this area include PaperBridge, which introduces a human-AI co-exploration system for crafting research narratives, and PhysGym, which presents a novel benchmark suite for evaluating LLM-based scientific reasoning in interactive physics environments. Overall, the field is experiencing a shift towards more collaborative and dynamic approaches to research, with AI playing an increasingly important role in facilitating and accelerating scientific progress.
Human-AI Collaboration in Research
Sources
PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration
PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
Understanding Large Language Models' Ability on Interdisciplinary Research
Interaction as Intelligence: Deep Research With Human-AI Partnership
ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry
AI for Better UX in Computer-Aided Engineering: Is Academia Catching Up with Industry Demands? A Multivocal Literature Review
LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
Disaster Informatics after the COVID-19 Pandemic: Bibliometric and Topic Analysis based on Large-scale Academic Literature