Abhishek Akkur
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Abhishek Akkur has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chia-Tung Ho
NVIDIA, Santa Clara, CA, USA
2 shared publications - Haoyu Yang
NVIDIA Corp., Austin, TX, USA
2 shared publications - Bing-Yue Wu
Arizona State University, Tempe, AZ, USA
1 shared publication - Brucek Khailany
NVIDIA, Santa Clara, California 95051, USA
1 shared publication - Chen-Chia Chang
Duke University
1 shared publication - Haoxing Ren
NVIDIA Corporation, Austin, TX, USA
1 shared publication
Latest Publications
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Special Research Session: Toward Agentic Solution for DRC Challenges in Digital VLSI Design
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessSpecial Research Session: Toward Agentic Solution for DRC Challenges in Digital VLSI Design
- Open Access
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 121-130
Invited: Polymath: Self-Improving Hierarchical Workflow for Multi-Domain Problem Solving
Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. However, building agents for diverse applications by manually embedding foundation models into agentic systems such as Chain-of-Thought, Self-Reflection, and ReACT through text interfaces limits scalability and efficiency. Recently, researchers have explored automating workflow generation using code-based representations, but most methods depend on labeled data, limiting their applicability to real-world, dynamic hardware design problems. We introduce Polymath, a self-improving agent with a dynamic hierarchical workflow that combines task flow graphs with code-represented workflows to address these challenges. Polymath employs an experience-driven optimization framework that integrates multi-level graph optimization using surrogate scores from historical evaluations with a self-reflection-guided evolutionary algorithm for workflow refinement, enabling unsupervised self-improvement without labeled data. Experiments show that Polymath outperforms a leading commercial agentic system by 16.23% pass@1 and 11.47% pass@3 on hardware benchmarks, and achieves an average 8.1% improvement over state-of-the-art baselines on coding, math, and multi-turn QA tasks.
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 121-130
Open AccessInvited: Polymath: Self-Improving Hierarchical Workflow for Multi-Domain Problem Solving
Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. However, building agents for diverse applications by manually embedding foundation models into agentic systems such as Chain-of-Thought, Self-Reflection, and ReACT through text interfaces limits scalability and efficiency. Recently, researchers have explored automating workflow generation using code-based representations, but most methods depend on labeled data, limiting their applicability to real-world, dynamic hardware design problems. We introduce Polymath, a self-improving agent with a dynamic hierarchical workflow that combines task flow graphs with code-represented workflows to address these challenges. Polymath employs an experience-driven optimization framework that integrates multi-level graph optimization using surrogate scores from historical evaluations with a self-reflection-guided evolutionary algorithm for workflow refinement, enabling unsupervised self-improvement without labeled data. Experiments show that Polymath outperforms a leading commercial agentic system by 16.23% pass@1 and 11.47% pass@3 on hardware benchmarks, and achieves an average 8.1% improvement over state-of-the-art baselines on coding, math, and multi-turn QA tasks.