# Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team

arXiv: https://arxiv.org/abs/2506.14234 · HTML: https://mlsanity.com/paper/2506.14234/

## Key facts

- Cited by 13 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 28 of its 70 references that are in the map.
- First posted on arXiv 17 Jun 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, 28 of 28)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset](https://mlsanity.com/paper/2504.16891/) (2025)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [OpenCodeReasoning: Advancing Data Distillation for Competitive Coding](https://mlsanity.com/paper/2504.01943/) (2025)
- [ACECODER: Acing Coder RL via Automated Test-Case Synthesis](https://mlsanity.com/paper/2502.01718/) (2025)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning](https://mlsanity.com/paper/2502.11271/) (2025)
- [rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset](https://mlsanity.com/paper/2505.21297/) (2025)
- [AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time](https://mlsanity.com/paper/2505.24863/) (2025)
- [AI Debate Aids Assessment of Controversial Claims](https://mlsanity.com/paper/2506.02175/) (2025)
- [TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text](https://mlsanity.com/paper/2505.11988/) (2025)

## Built on by (most cited first, 13 of 13)

- [AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2507.21836/) (2025)
- [SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?](https://mlsanity.com/paper/2602.03916/) (2026)
- [SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning](https://mlsanity.com/paper/2511.08151/) (2025)
- [From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection](https://mlsanity.com/paper/2511.00181/) (2025)
- [MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration](https://mlsanity.com/paper/2509.05933/) (2025)
- [Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning](https://mlsanity.com/paper/2601.23032/) (2026)
- [Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning](https://mlsanity.com/paper/2606.24428/) (2026)
- [Poison with Style: A Practical Poisoning Attack on Code Large Language Models](https://mlsanity.com/paper/2605.27631/) (2026)
- [ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video](https://mlsanity.com/paper/2508.09818/) (2025)
- [GANDiff FR: Hybrid GAN Diffusion Synthesis for Causal Bias Attribution in Face Recognition](https://mlsanity.com/paper/2508.11334/) (2025)
- [Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali](https://mlsanity.com/paper/2601.17764/) (2026)
- [Pattern Recognition Tasks with Personalized Federated Learning](https://mlsanity.com/paper/2605.27816/) (2026)
- [MARS: Multi-Specialist LLM Relay System for Competitive Programming](https://mlsanity.com/paper/2608.23918/) (2026)

## Abstract (arXiv)

Despite impressive progress on complex reasoning, current large language models (LLMs) typically operate in isolation - treating each problem as an independent attempt, without accumulating or integrating experiential knowledge. In contrast, expert problem solvers - such as Olympiad or programming contest teams - leverage a rich tapestry of experiences: absorbing mentorship from coaches, developing intuition from past problems, leveraging knowledge of tool usage and library functionality, adapting strategies based on the expertise and experiences of peers, continuously refining their reasoning through trial and error, and learning from other related problems even during competition. We introduce Xolver, a training-free multi-agent reasoning framework that equips a black-box LLM with a persistent, evolving memory of holistic experience. Xolver integrates diverse experience modalities, including external and self-retrieval, tool use, collaborative interactions, agent-driven evaluation, and iterative refinement. By learning from relevant strategies, code fragments, and abstract reasoning patterns at inference time, Xolver avoids generating solutions from scratch - marking a transition from isolated inference toward experience-aware language agents. Built on both open-weight and proprietary models, Xolver consistently outperforms specialized reasoning agents. Even with lightweight backbones (e.g., QWQ-32B), it often surpasses advanced models including Qwen3-235B, Gemini 2.5 Pro, o3, and o4-mini-high. With o3-mini-high, it achieves new best results on GSM8K (98.1%), AIME'24 (94.4%), AIME'25 (93.7%), Math-500 (99.8%), and LiveCodeBench-V5 (91.6%) - highlighting holistic experience learning as a key step toward generalist agents capable of expert-level reasoning. Code and data are available at https://kagnlp.github.io/xolver.github.io/.