A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Junda He, Christoph Treude, David Lo
A systematic literature review of LLM-based multi-agent systems across the software development lifecycle, with case studies, research gaps, and a forward-looking agenda.
B.‐C. CHEN, Zhaofeng Zhang, Nicolas Langrené, et al.
This review surveys foundational and advanced prompt engineering techniques for LLMs and VLMs, evaluates them with subjective and objective metrics, and examines prompt engineering's role in AI security.
Bo Wen, Xin Zhang
SOLOMON is a neuro-inspired LLM reasoning network architecture that enhances domain adaptability via prompt engineering and in-context learning, outperforming baselines and matching o1-preview in semiconductor layout design.
Neura Market
81% of n8n workflow templates that call an external system declare no error handling at all — no retry, no timeout, no error branch. A structural analysis of 5,147 deduplicated automation templates, read from their own executable specifications.
Soorya Ram Shimgekar, Michelle Hu, Dorisa Shehi, et al.
An evidence-linked, rubric-grounded multi-agent pipeline for automated heart-failure feature engineering from EHR data, improving phenotyping AUROC and enabling auditable features.
Unknown
SPARE is a training-free method using pre-trained sparse auto-encoders to steer knowledge selection in LLMs by editing internal representations.
Unknown
This paper applies representation engineering to identify and steer internal representations of high-level human preferences in LLMs, improving alignment.
Unknown
Proposes Adversarial Representation Engineering (ARE), a general model editing framework that efficiently edits large language models by leveraging representation engineering.
Unknown
This paper proposes a representation engineering approach that reads LLM activations from the residual stream during reasoning tasks to improve performance.
Unknown
SHARP is a representation-level intervention framework that modulates hallucination in LVLMs by steering internal representations.
Unknown
Proposes MRRE, a training-free inference-time method using representation engineering to enhance multilingual reasoning in LLMs and LVLMs without additional training data.
Bowei Tian, Xuntao Lyu, Meng Liu, et al.
This paper provides a theoretical and empirical analysis of why representation engineering works in vision-language models, offering a unified framework and practical insights.