PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity

• URL: http://arxiv.org/abs/2607.20268v1
• Date: Wed, 22 Jul 2026 15:20:53 GMT
• Title: PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
• Abstract summary: PoTRE (Poly-Topological Reasoning Ensembles) is a heterogeneous framework that decouples inference into four agents.<n>We evaluate PoTRE on three frontier benchmarks: ARC-AGI-2, Humanity's Last Exam (HLE), and PRBench Finance.<n>PoTRE achieves state-of-the-art accuracy of 49.92% on HLE, surpassing the previous best official score.
• Score: 0.24554686192257422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterative error correction. Furthermore, standard single-stream prompting proves brittle when models encounter novel abstractions or rigorous domain constraints. We introduce PoTRE (Poly-Topological Reasoning Ensembles), a heterogeneous framework that decouples inference into four agents: (1) Adversarial Refinement Agent, (2) Hierarchical strategic Planning Agent, (3) Spectrum Search Agent, and (4) Direct Chain Agent. A final Task-Adaptive Aggregation Layer dynamically reconciles these perspectives -- via final candidate selection, semantic synthesis, or neuro-symbolic verification -- to produce a robust global solution. We evaluate PoTRE on three frontier benchmarks: ARC-AGI-2, Humanity's Last Exam (HLE), and PRBench Finance. PoTRE achieves state-of-the-art accuracy of 49.92% on HLE, surpassing the previous best official score. We demonstrate that this architectural heterogeneity achieves improved reasoning performance using similar or fewer inference tokens compared to heavily scaled homogeneous baselines.

Related papers

• Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP [3.774094352572544]
  Programmatic state abstraction delivers the largest returns per token spent.<n>Distributing deliberation tools across a hierarchy degrades performance relative to hierarchy alone.<n>Hierarchical decomposition without deliberation achieves the best absolute performance for most models.
  arXiv  Detail & Related papers  (2026-05-15T17:23:08Z)
• Council Mode: Mitigating Hallucination and Bias in LLMs via Multi-Agent Consensus [11.49727358706339]
  Large Language Models (LLMs) have achieved remarkable capabilities across diverse natural language processing tasks.<n>LLMs frequently suffer from hallucinations, generating plausible but factually incorrect content.<n>We propose the Council Mode, a novel multi-agent consensus framework.<n>We implement and evaluate this architecture within an open-source AI workspace.
  arXiv  Detail & Related papers  (2026-04-03T09:40:43Z)
• Reasoning-Driven Multimodal LLM for Domain Generalization [72.00754603114187]
  We study the role of reasoning in domain generalization using DomainBed-Reasoning dataset.<n>We propose RD-MLDG, a framework with two components: MTCT (Multi-Task Cross-Training) and SARR (Self-Aligned Reasoning Regularization)<n>Experiments on standard DomainBed datasets demonstrate that RD-MLDG achieves complementary state-of-the-art performances.
  arXiv  Detail & Related papers  (2026-02-27T08:10:06Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• An Analysis of Architectural Impact on LLM-based Abstract Visual Reasoning: A Systematic Benchmark on RAVEN-FAIR [0.0]
  GPT-4.1-Mini consistently achieved the highest overall accuracy across all architectures.<n>Each model exhibited distinct sensitivity patterns to architectural design, underscoring that reasoning effectiveness remains model-specific.
  arXiv  Detail & Related papers  (2025-11-14T22:50:22Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling [56.45844907505722]
  We propose DecoupleSearch, a framework that decouples planning and search processes using dual value models.<n>Our approach constructs a reasoning tree, where each node represents planning and search steps.<n>During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models.
  arXiv  Detail & Related papers  (2025-09-07T13:45:09Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Why Do Multi-Agent LLM Systems Fail? [87.90075668488434]
  We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks.<n>We build the first Multi-Agent System Failure taxonomy (MAST)<n>We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent)
  arXiv  Detail & Related papers  (2025-03-17T19:04:38Z)
• A NotSo Simple Way to Beat Simple Bench [0.0]
  This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs)<n>We propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness.<n>Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts.
  arXiv  Detail & Related papers  (2024-12-12T16:04:31Z)
• Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation [49.27250832754313]
  We present AgentCOT, a llm-based autonomous agent framework. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. We introduce two new strategies to enhance the performance of AgentCOT.
  arXiv  Detail & Related papers  (2024-09-19T02:20:06Z)

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.