PoTRE：一种基于认知异构性的测试时推理框架
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
这篇论文提出了PoTRE，用四个不同角色的智能体协作推理，在HLE上拿了新SOTA，而且比单纯堆参数的模型更省计算量。
PoTRE将推理过程解耦为四个代理：对抗细化代理、分层策略规划代理、频谱搜索代理和直接链代理，并通过任务自适应聚合层融合。
在ARC-AGI-2、HLE和PRBench Finance三个基准上评估，PoTRE在HLE上达到49.92%的准确率，超越此前官方最佳成绩。
该框架使用相似或更少的推理token实现了优于同质基线的推理性能。
PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneity
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.
This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include PoTRE, 多智能体推理, 推理模型, ARC-AGI-2.
Source attribution: curated from arXiv cs.AI (@Anmol Kankariya, Sercan Ö. Arık).
