# MAXS: Meta-Adaptive Exploration with LLM Agents

arXiv: https://arxiv.org/abs/2601.09259 · HTML: https://mlsanity.com/paper/2601.09259/

## Key facts

- Cited by 1 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 27 of its 43 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## 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, 27 of 27)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark](https://mlsanity.com/paper/2501.05444/) (2025)
- [BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling](https://mlsanity.com/paper/2406.00832/) (2024)
- [MiMo-VL Technical Report](https://mlsanity.com/paper/2506.03569/) (2025)
- [EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism](https://mlsanity.com/paper/2312.04916/) (2023)
- [Non-myopic Generation of Language Models for Reasoning and Planning](https://mlsanity.com/paper/2410.17195/) (2024)
- [Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning](https://mlsanity.com/paper/2504.08672/) (2025)
- [KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search](https://mlsanity.com/paper/2501.18922/) (2025)
- [MUR: Momentum Uncertainty guided Reasoning for Large Language Models](https://mlsanity.com/paper/2507.14958/) (2025)
- [MASTER: A Multi-Agent System with LLM Specialized MCTS](https://mlsanity.com/paper/2501.14304/) (2025)
- [MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization](https://mlsanity.com/paper/2503.16874/) (2025)
- [Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent](https://mlsanity.com/paper/2409.11527/) (2024)
- [Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2511.01016/) (2025)
- [Embodied CoT Distillation From LLM To Off-the-shelf Agents](https://mlsanity.com/paper/2412.11499/) (2024)
- [Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction](https://mlsanity.com/paper/2505.06303/) (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)

## Built on by (most cited first, 1 of 1)

- [Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement](https://mlsanity.com/paper/2601.13481/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer from (i) locally myopic generation, due to the absence of lookahead, and (ii) trajectory instability, where minor early errors can escalate into divergent reasoning paths. These issues make it difficult to balance global effectiveness and computational efficiency. To address these two issues, we propose meta-adaptive exploration with LLM agents https://github.com/exoskeletonzj/MAXS, a meta-adaptive reasoning framework based on LLM Agents that flexibly integrates tool execution and reasoning planning. MAXS employs a lookahead strategy to extend reasoning paths a few steps ahead, estimating the advantage value of tool usage, and combines step consistency variance and inter-step trend slopes to jointly select stable, consistent, and high-value reasoning steps. Additionally, we introduce a trajectory convergence mechanism that controls computational cost by halting further rollouts once path consistency is achieved, enabling a balance between resource efficiency and global effectiveness in multi-tool reasoning. We conduct extensive empirical studies across three base models (MiMo-VL-7B, Qwen2.5-VL-7B, Qwen2.5-VL-32B) and five datasets, demonstrating that MAXS consistently outperforms existing methods in both performance and inference efficiency. Further analysis confirms the effectiveness of our lookahead strategy and tool usage.