Anmol Kankariya
Anmol Kankariya works in Applied AI, where he focuses on innovating and transforming cutting-edge artificial intelligence research into high-impact, actionable solutions for enterprise customers. He specializes in translating advancements in Large Language Models (LLMs) and Generative AI into robust, scalable architectures that integrate seamlessly into complex business environments. Alongside his industry work, Anmol is actively engaged in AI and machine learning research, developing novel approaches to solve real-world challenges. His work centers on building highly efficient, reliable, and secure AI systems that empower global enterprises to adopt next-generation intelligent technologies.
Research Areas
Authored Publications
Sort By
Preview 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.
View details
