Research StagesIdeation 19
Scientific Inspiration Machines Optimized for Novelty
An LLM-based Scientific Paper Idea Proposer
Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback
Improved Scientific Idea Generation by A LLM-Based Multi-Agent System
Interactive Research Ideation System for Accelerating Scientific Discovery
Towards Systematic and Principled Benchmarking for Hypothesis Generation
A Synergistic Approach to Hypothesis Generation
AI Research Idea Generation Benchmark
Benchmarking Large Language Models for Research Idea Generation
Hypothesis Generation Using Structured Paper Data
A Comprehensive Evaluation
A System for Scientifically Creative Idea Generation
Automating Knowledge-Grounded and Transparent Research Ideation with Multi-Agent Collaboration
Literature 12
On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
Academic Survey Automation via Large Language Models
A Retrieval Benchmark for Scientific Literature Search
Synthesizing Scientific Literature into Tables using Language Models
A Toolkit for Scientific Literature Review
Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search
Automated Generation of Related Work Analysis on the arXiv Corpus
Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?
Quality-Aware Scientific Survey Generation with Large Language Models
Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research
Experiments 8
Adaptive Knowledgeable Agent for Automated Data Science
End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation
A Multi-Agent System for End-to-end Machine Learning Automation
Automatic AI Experiment Reproduction with Paper Lineage
Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search
Evaluating Language Agents on Machine Learning Experimentation
Can AI Conduct AI Research Experiments?
Writing 15
An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers
Towards Multimodal Poster Automation from Scientific Papers
Designing Structured Visuals from Scratch
Automatic Video Generation from Scientific Papers
Training Large Language Models for Academic Writing with Accurate Citations
How to Adapt LLMs for Scientific Literature Understanding
A Dataset of End-to-End Scholarly Writing Process
A Multi-Agent Framework for Automated AI Research Paper Writing
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Text-Guided Synthesis of Scientific Vector Graphics with TikZ
Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement
New Benchmark and Methods
GPT-4 Summarization with Chain of Density Prompting
Review 15
A Specialized Large Language Model for Generating Critical Scientific Paper Reviews
Exploring Peer Review Dynamics with LLM Agents
Optimizing Review Generation Through Prompt Generation
Critique Paper (Meta-)Reviewing
A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
SPOT-a Benchmark for Automated Verification of Scientific Research
The AAAI-26 AI Review Pilot
Verifying Scientific Claims
Improving scientific claim verification with weak supervision and full-document context
A Large Dataset for Evidence-based Scientific Claim Verification
Knowledge & Tools 3
Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
Nothing matches those filters.