NLP / Agents — Paper Notes
LLMs, scientific agents, and language-model tooling
2018
2019
ACL-2019 Improving Robustness of Neural Machine Translation with Multi-task Learning
arXiv-2019 RoBERTa：A Robustly Optimized BERT Pretraining Approach
OpenAI-2019 Language Models are Unsupervised Multitask Learners
arXiv-2019 Unified Language Model Pre-training for Natural Language Understanding and Generation
ICML-2019 Parameter-Efficient Transfer Learning for NLP
2021
2022
arXiv-2022 Holistic Evaluation of Language Models
NAACL-2022 MoEBERT：from BERT to Mixture-of-Experts via Importance-Guided Adaptation
arXiv-2022 Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
OpenAI-2022 Training language models to follow instructions with human feedback
ICLR-2022 LoRA：Low-Rank Adaptation of Large Language Models
NeurIPS-2022 Chain of Thought Prompting Elicits Reasoning in Large Language Models
Journal of Machine Learning Research-2022 Switch Transformers：Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
2025
arXiv-2025 Evaluating Large Language Models in Scientific Discovery
NeurIPS-2025 AI-Researcher：Autonomous Scientific Innovation
EMNLP-2025 From Automation to Autonomy：A Survey on Large Language Models in Scientific Discovery
ACEBench：Who Wins the Match Point in Tool Usage
arXiv-2025 The AI Scientist-v2：Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Nature Computational Science-2025 SciToolAgent：A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
