---
id: "/tags/research/"
title: "Research"
creator: null
url: "https://skillissue.dev/tags/research/"
level: null
category: null
models: null
source_date: null
date_added: null
---

# Research

[Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md)

8 resources

- 

### [Context Rot: How Increasing Input Tokens Impacts LLM Performance](/e/chroma-context-rot/index.md)

by [Chroma](https://www.trychroma.com/research/context-rot)

Measures how output quality drops as input length grows.

Advanced · any · date not stated

- 

### [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](/e/schulhoff-the-prompt-report/index.md)

by [Sander Schulhoff et al.](https://arxiv.org/abs/2406.06608)

A broad research taxonomy for comparing prompting techniques and finding their sources.

Advanced · any · 2024-06-06

- 

### [Self-Consistency Improves Chain of Thought Reasoning in Language Models](/e/wang-self-consistency/index.md)

by [Xuezhi Wang et al.](https://arxiv.org/abs/2203.11171)

Sample several reasoning paths and take the majority answer.

Advanced · any · 2022-03-21

- 

### [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](/e/wei-chain-of-thought-prompting/index.md)

by [Jason Wei et al.](https://arxiv.org/abs/2201.11903)

Early research on using worked reasoning examples to improve performance on reasoning tasks.

Advanced · any · 2022-01-28

- 

### [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](/e/greshake-indirect-prompt-injection/index.md)

by [Kai Greshake et al.](https://arxiv.org/abs/2302.12173)

Foundational public research on indirect prompt injection. Linked only; no payloads reproduced.

Expert · any · 2023-02-23

- 

### [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](/e/yang-swe-agent/index.md)

by [John Yang et al.](https://arxiv.org/abs/2405.15793)

Research on how the agent-computer interface influences software-engineering performance.

Expert · any · 2024-05-06

- 

### [ReAct: Synergizing Reasoning and Acting in Language Models](/e/yao-react/index.md)

by [Shunyu Yao et al.](https://arxiv.org/abs/2210.03629)

Research on combining reasoning with environment actions, a useful reference for agent-loop design.

Expert · any · 2022-10-06

- 

### [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](/e/yao-tree-of-thoughts/index.md)

by [Shunyu Yao et al.](https://arxiv.org/abs/2305.10601)

Search over branching reasoning steps; basis for many planning approaches.

Expert · any · 2023-05-17