STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision

• URL: http://arxiv.org/abs/2605.19338v1
• Date: Tue, 19 May 2026 04:20:43 GMT
• Title: STAR-PólyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision
• Abstract summary: We introduce STAR-PlyaMath, a multi-agent framework for extended, long-horizon reasoning.<n> STAR-PlyaMath is structured as an orchestrated state machine with nested challenge-step-replan loops.<n>It achieves perfect scores on all eight top-tier competition benchmarks.
• Score: 25.371500356523896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, long-horizon reasoning, existing systems continue to suffer from fundamental reliability issues: hallucination accumulation, memory fragmentation, and imbalanced reasoning-tool trade-offs. In this paper, we introduce STAR-PólyaMath, a multi-agent framework that systematically addresses these challenges through meta-level supervision and structured Reasoner-Verifier interaction. STAR-PólyaMath is structured as an orchestrated state machine with nested challenge-step-replan loops, governed by a reasoning-free Python orchestrator that separates control from inference and bounds error propagation through trace-back and re-planning. Our key innovation is a persistent Meta-Strategist that maintains cross-attempt memory and exercises meta-level control by issuing high-level strategic guidance or mandatory directives, so the system can escape unproductive loops rather than stagnate or over-rely on tools. STAR-PólyaMath achieves state-of-the-art results on all eight top-tier competition benchmarks: AIME 2025-2026, MathArena Apex Shortlist, MathArena Apex 2025, Putnam 2025, IMO 2025, HMMT February 2026, and USAMO 2026. It obtains perfect scores on AIMEs, Putnam, and HMMT, and shows its largest margin on Apex 2025, scoring 93.75% compared with 80.21% by the strongest baseline GPT-5.5. Ablation studies show that the gains arise from the framework's orchestration rather than from model-level diversity since removing key components or substituting in mixed backbones consistently weakens performance. Code is available at https://github.com/Julius-Woo/STAR-PolyaMath.

Related papers

• Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling [108.48818215929494]
  We introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver.<n>We train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps.<n>The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens.
  arXiv  Detail & Related papers  (2026-05-13T10:13:26Z)
• CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning [17.364321308755667]
  CoT2-Meta is a training-free metacognitive reasoning framework.<n>It combines object-level chain-of-thought generation with meta-level control over partial reasoning trajectories.<n>It consistently outperforms strong single-path, sampling-based, and search-based baselines.
  arXiv  Detail & Related papers  (2026-03-30T07:59:47Z)
• RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty [102.02839046225468]
  RankLLM is a novel framework designed to quantify both question difficulty and model competency.<n>We evaluate 30 models on 35,550 questions across multiple domains.
  arXiv  Detail & Related papers  (2026-02-12T21:28:46Z)
• Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision [15.319195064020393]
  Nemotron-Math is a large-scale mathematical reasoning dataset containing 7.5M solution traces.<n>The dataset integrates 85K curated AoPS problems with 262K community-sourced StackExchange-Math problems.<n>Nemotron-Math consistently outperforms the original OpenMathing on matched AoPS problems.
  arXiv  Detail & Related papers  (2025-12-17T14:37:41Z)
• Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving [65.02106674311908]
  This paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning.<n>By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces.<n> Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists.
  arXiv  Detail & Related papers  (2025-12-11T15:26:28Z)
• KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems [36.17807193758863]
  KompeteAI is a novel AutoML framework with dynamic solution space exploration.<n>We introduce KompeteAI, a novel AutoML framework with dynamic solution space exploration.<n>We propose Kompete-bench to address limitations in MLE-Bench, where KompeteAI also achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-08-13T20:29:56Z)
• MathArena: Evaluating LLMs on Uncontaminated Math Competitions [4.655668424508813]
  MathArena is a new benchmark for evaluating large language models (LLMs)<n>It is based on the following key insight: recurring math competitions provide a stream of high-quality, challenging problems.<n>MathArena is also the first benchmark for proof-writing capabilities.
  arXiv  Detail & Related papers  (2025-05-29T09:28:06Z)
• Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models [86.45058529521258]
  OlymMATH is a novel Olympiad-level mathematical benchmark designed to rigorously test the complex reasoning capabilities of LLMs.<n>OlymMATH features 200 meticulously curated problems, each manually verified and available in parallel English and Chinese versions.
  arXiv  Detail & Related papers  (2025-03-27T11:20:17Z)
• MetaScale: Test-Time Scaling with Evolving Meta-Thoughts [51.35594569020857]
  Experimental results demonstrate that MetaScale consistently outperforms standard inference approaches.<n> METASCALE scales more effectively with increasing sampling budgets and produces more structured, expert-level responses.
  arXiv  Detail & Related papers  (2025-03-17T17:59:54Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.