# MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization

arXiv: https://arxiv.org/abs/2503.16874 · HTML: https://mlsanity.com/paper/2503.16874/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://mlsanity.com/paper/2306.02224/) (2023)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization](https://mlsanity.com/paper/2310.16427/) (2023)
- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models](https://mlsanity.com/paper/2306.03082/) (2023)
- [Prompt Engineering a Prompt Engineer](https://mlsanity.com/paper/2311.05661/) (2023)
- [TEMPERA: Test-Time Prompting via Reinforcement Learning](https://mlsanity.com/paper/2211.11890/) (2022)
- [Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling](https://mlsanity.com/paper/2305.09993/) (2023)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2501.18119/) (2025)
- [GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction](https://mlsanity.com/paper/2503.11227/) (2025)
- [A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction](https://mlsanity.com/paper/2403.09721/) (2024)

## Built on by (most cited first, 15 of 15)

- [MUR: Momentum Uncertainty guided Reasoning for Large Language Models](https://mlsanity.com/paper/2507.14958/) (2025)
- [Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2511.01016/) (2025)
- [Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction](https://mlsanity.com/paper/2505.06303/) (2025)
- [xChemAgents: Agentic AI for Explainable Quantum Chemistry](https://mlsanity.com/paper/2505.20574/) (2025)
- [GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines](https://mlsanity.com/paper/2508.06226/) (2025)
- [LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence](https://mlsanity.com/paper/2512.04578/) (2025)
- [Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing](https://mlsanity.com/paper/2512.00881/) (2025)
- [Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning Architectures](https://mlsanity.com/paper/2508.05116/) (2025)
- [MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization](https://mlsanity.com/paper/2510.16635/) (2025)
- [MAXS: Meta-Adaptive Exploration with LLM Agents](https://mlsanity.com/paper/2601.09259/) (2026)
- [GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams](https://mlsanity.com/paper/2603.19252/) (2026)
- [SPEAR: Code-Augmented Agentic Prompt Optimization](https://mlsanity.com/paper/2605.26275/) (2026)
- [Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution](https://mlsanity.com/paper/2606.20475/) (2026)
- [OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents](https://mlsanity.com/paper/2603.03005/) (2026)
- [MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning](https://mlsanity.com/paper/2603.18577/) (2026)

## Abstract (arXiv)

Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimization (APO) aims to overcome the cognitive biases of manually crafted prompts and explore a broader prompt design space. However, existing APO methods often suffer from rigid template structures and inefficient exploration in the prompt space. To this end, we propose a Multi-Agent Adaptive Reasoning with Socratic guidance framework (MARS) for APO. MARS consists of five complementary agents and formulates the optimization process as a Partially Observable Markov Decision Process (POMDP), enabling adaptive prompt refinement through explicit state modeling and interactive feedback. Specifically, a Planner agent generates flexible optimization trajectories, a Teacher-Critic-Student triad engages in Socratic-style dialogue to iteratively optimize the prompt based on pseudo-gradient signals in the text space, and a Target agent executes the prompt in downstream tasks to provide performance feedback. MARS integrates reasoning, feedback, and state transition into a unified hidden-state evolution process, improving both the effectiveness and interpretability of optimization. Extensive experiments on multiple datasets demonstrate that MARS outperforms existing APO methods in terms of optimization performance, search efficiency, and interpretability.