# Agent Instructs Large Language Models to be General Zero-Shot Reasoners

arXiv: https://arxiv.org/abs/2310.03710 · HTML: https://mlsanity.com/paper/2310.03710/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 0 of its 106 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Built on by (most cited first, 30 of 32)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers](https://mlsanity.com/paper/2410.05273/) (2024)
- [The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models](https://mlsanity.com/paper/2401.05618/) (2024)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [Understanding the Weakness of Large Language Model Agents within a Complex Android Environment](https://mlsanity.com/paper/2402.06596/) (2024)
- [TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation](https://mlsanity.com/paper/2402.10178/) (2024)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://mlsanity.com/paper/2405.06682/) (2024)
- [Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers](https://mlsanity.com/paper/2402.17564/) (2024)
- [A Zero-Shot Language Agent for Computer Control with Structured Reflection](https://mlsanity.com/paper/2310.08740/) (2023)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models](https://mlsanity.com/paper/2401.07115/) (2024)
- [Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection](https://mlsanity.com/paper/2411.07446/) (2024)
- [Measuring Social Norms of Large Language Models](https://mlsanity.com/paper/2404.02491/) (2024)
- [Can We Verify Step by Step for Incorrect Answer Detection?](https://mlsanity.com/paper/2402.10528/) (2024)
- [LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess](https://mlsanity.com/paper/2512.01992/) (2025)
- [Measuring Vision-Language STEM Skills of Neural Models](https://mlsanity.com/paper/2402.17205/) (2024)
- [An Empirical Study of Agent Developer Practices in AI Agent Frameworks](https://mlsanity.com/paper/2512.01939/) (2025)
- [DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs](https://mlsanity.com/paper/2401.05190/) (2024)
- [Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study](https://mlsanity.com/paper/2403.10499/) (2024)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [MOC: Multi-Order Communication in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2606.02359/) (2026)
- [Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2412.18351/) (2024)
- [Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models](https://mlsanity.com/paper/2507.18858/) (2025)
- [The Tyranny of Possibilities in the Design of Task-Oriented LLM Systems: A Scoping Survey](https://mlsanity.com/paper/2312.17601/) (2023)
- [Towards Dialogues for Joint Human-AI Reasoning and Value Alignment](https://mlsanity.com/paper/2405.18073/) (2024)
- [Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning](https://mlsanity.com/paper/2407.04787/) (2024)
- [Predicting Task Performance with Context-aware Scaling Laws](https://mlsanity.com/paper/2510.14919/) (2025)
- [LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge](https://mlsanity.com/paper/2504.21132/) (2025)
- [From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews](https://mlsanity.com/paper/2512.11661/) (2025)

## Abstract (arXiv)

We introduce a method to improve the zero-shot reasoning abilities of large language models on general language understanding tasks. Specifically, we build an autonomous agent to instruct the reasoning process of large language models. We show this approach further unleashes the zero-shot reasoning abilities of large language models to more tasks. We study the performance of our method on a wide set of datasets spanning generation, classification, and reasoning. We show that our method generalizes to most tasks and obtains state-of-the-art zero-shot performance on 20 of the 29 datasets that we evaluate. For instance, our method boosts the performance of state-of-the-art large language models by a large margin, including Vicuna-13b (13.3%), Llama-2-70b-chat (23.2%), and GPT-3.5 Turbo (17.0%). Compared to zero-shot chain of thought, our improvement in reasoning is striking, with an average increase of 10.5%. With our method, Llama-2-70b-chat outperforms zero-shot GPT-3.5 Turbo by 10.2%.