Retrieval augmented generation (rag) and beyond: A comprehensive survey on how to make your llms use external data more wisely

S Zhao, Y Yang, Z Wang, Z He, LK Qiu… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) augmented with external data have demonstrated
remarkable capabilities in completing real-world tasks. Techniques for integrating external …

Agent hospital: A simulacrum of hospital with evolvable medical agents

J Li, Y Lai, W Li, J Ren, M Zhang, X Kang… - arxiv preprint arxiv …, 2024 - arxiv.org
The recent rapid development of large language models (LLMs) has sparked a new wave of
technological revolution in medical artificial intelligence (AI). While LLMs are designed to …

Recursive introspection: Teaching language model agents how to self-improve

Y Qu, T Zhang, N Garg, A Kumar - arxiv preprint arxiv:2407.18219, 2024 - arxiv.org
A central piece in enabling intelligent agentic behavior in foundation models is to make them
capable of introspecting upon their behavior, reasoning, and correcting their mistakes as …

Star-gate: Teaching language models to ask clarifying questions

C Andukuri, JP Fränken, T Gerstenberg… - arxiv preprint arxiv …, 2024 - arxiv.org
When prompting language models to complete a task, users often leave important aspects
unsaid. While asking questions could resolve this ambiguity\citep [GATE;][]{li2023eliciting} …

Quiet-star: Language models can teach themselves to think before speaking

E Zelikman, G Harik, Y Shao, V Jayasiri… - arxiv preprint arxiv …, 2024 - arxiv.org
When writing and talking, people sometimes pause to think. Although reasoning-focused
works have often framed reasoning as a method of answering questions or completing …

Recursive introspection: Teaching LLM agents how to self-improve

Y Qu, T Zhang, N Garg, A Kumar - ICML 2024 Workshop on …, 2024 - openreview.net
A central piece in enabling intelligent agentic behavior in foundation models is to make them
capable of introspecting upon their behavior, to reason and correct their mistakes. However …

Retrieved in-context principles from previous mistakes

H Sun, Y Jiang, B Wang, Y Hou, Y Zhang, P **e… - arxiv preprint arxiv …, 2024 - arxiv.org
In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs)
to downstream tasks using correct input-output examples. Recent advances have attempted …

Neural-symbolic collaborative distillation: Advancing small language models for complex reasoning tasks

H Liao, S He, Y Xu, Y Zhang, K Liu, J Zhao - arxiv preprint arxiv …, 2024 - arxiv.org
In this paper, we propose $\textbf {Ne} $ ural-$\textbf {Sy} $ mbolic $\textbf {C} $ ollaborative
$\textbf {D} $ istillation ($\textbf {NesyCD} $), a novel knowledge distillation method for …

Investigating the potential of using large language models for scheduling

D Jobson, Y Li - Proceedings of the 1st ACM International Conference …, 2024 - dl.acm.org
The inaugural ACM International Conference on AI-powered Software introduced the AIware
Challenge, prompting researchers to explore AI-driven tools for optimizing conference …

Wrong-of-thought: An integrated reasoning framework with multi-perspective verification and wrong information

Y Zhang, Q Chen, J Zhou, P Wang, J Si, J Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of
Large Language Models (LLMs), attracting increasing attention from researchers. One …