Storyteller · AI Researcher

Karthik
Valmeekam

PhD, Arizona State IBM Fellow Amazon AGI

Download CV

About

The story so far — I am a

Rigorously formalized ideas are great stories to tell.

My Story

I was born in Hyderabad, India but my childhood was shaped by two vastly different places; the sub-tropical highlands of Addis Ababa, Ethiopia (from K.G. to 5th Grade) and the sun-scorching deserts of Ibra, Oman (5th to 10th Grade). Wherever I went, I carried my love for stories and thought of myself as a storyteller.

After my frivolous attempt at cracking the JEE, I joined Vellore Institute of Technology to explore and tell stories about Computers and Algorithms. During my Masters at Arizona State University, I discovered that rigorously formalized ideas are great stories to tell! That drove me to pursue research under the guidance of Prof. Subbarao Kambhampati.

Currently, my world revolves around Large Language Models (LLMs) and Planning. While many were caught up in the hype of LLMs' supposed planning capabilities—or panicking about them taking over the world—I was busy helping my group cut through the noise and ground the conversation. My efforts earned me the prestigious 🏆 IBM PhD Fellowship Award (2024) 🏆 in recognition of my work on the reasoning and planning abilities of LLMs.

When I'm not immersed in research, I channel my creativity into screenwriting, dancing, photography, and playing the keyboard. I also enjoy listening to a wide variety of music, ranging from heavy metal to carnatic ragas.

Featured

Recognition

ICAPS Distinguished Dissertation Award 2026
Dean’s Dissertation Award 2026
IBM PhD Fellowship 2024

For work on the reasoning & planning abilities of LLMs

Latest News

Education

Passing through the academic jungle

2021 - 2025

Arizona State University

Tempe, Arizona, US

PhD in Computer Science

GPA 4.0/4.0 • Graduate Research Assistant at Yochan under Prof. Subbarao Kambhampati

Dissertation: On the Role of Large Language Models in Planning

  • ICAPS Distinguished Dissertation Award (2026)
  • Dean’s Dissertation Award (2026)
2019 - 2021

Arizona State University

Tempe, Arizona, US

M.S. in Computer Science

GPA 4.0/4.0 • Graduate Research Assistant at Yochan under Prof. Subbarao Kambhampati

Thesis: Explainable Decision Support for Sequential Decision Making

  • Published at ICAPS 2022
2015 - 2019

Vellore Institute Of Technology

Vellore, Tamilnadu, India

B.Tech. in Computer Science

GPA 9.19/10.0 • Research Aide under Prof. Anuradha J • Vice-Chair Codechef-VIT

2013 - 2015

Narayana Junior College

Hyderabad, Telangana, India

Intermediate (11th & 12th)

Percentage: 95.1%

2007 - 2013

Indian School Ibra

Ibra, Oman

10th Std

GPA 9.8/10.0 • Computer Whizkid • Best Dancer

Experience

Learning never stops

Current Role

Amazon Science

Sunnyvale, California, US

Applied Scientist II

June 2025 - Present

Working in the AGI team to better Nova models.

Previous Experience

Amazon Science

Palo Alto, California, US

Applied Scientist Intern

May - Aug 2024

Worked on LLMs and Planning.

Skills & Technologies

Languages
Python · C++ · JavaScript · SQL · Bash
ML & Research
PyTorch · TensorFlow · HuggingFace · OpenCV · ROS
Infra & Tools
Docker · Kubernetes · AWS · Premiere Pro · Photoshop

Research

Formalizing curiosity

Selected work on the reasoning & planning abilities of LLMs

2026 ICML Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces
Subbarao Kambhampati, Karthik Valmeekam, Siddhant Bhambri, Vardhan Palod, Lucas Saldyt, Kaya Stechly, Soumya Rani Samineni, Durgesh Kalwar, Upasana Biswas NEW
2026 TMLR Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
Kaya Stechly*, Karthik Valmeekam*, Atharva Gundawar*, Vardhan Palod*, Subbarao Kambhampati NEW
2025 NYAS (How) Do reasoning models reason?
Subbarao Kambhampati, Kaya Stechly, Karthik Valmeekam
2025 TMLR A Systematic Evaluation of the Planning and Scheduling Abilities of o1
Karthik Valmeekam*, Kaya Stechly*, Atharva Gundawar, Subbarao Kambhampati
2025 ICLR On the Self-Verification Limitations of LLMs on Reasoning and Planning Tasks
Kaya Stechly*, Karthik Valmeekam*, Subbarao Kambhampati
2024 NeurIPS Chain of Thoughtlessness? An Analysis of CoT in Planning
Kaya Stechly*, Karthik Valmeekam*, Subbarao Kambhampati
2024 ICML LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks Spotlight
Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Kaya Stechly, et al.
2024 AAAI Tutorial On the role of large language models in planning
Subbarao Kambhampati, Karthik Valmeekam, Lin Guan
2023 NeurIPS On the Planning Abilities of Large Language Models--A Critical Investigation Spotlight
Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati
2023 NeurIPS Leveraging LLMs to Construct and Utilize World Models for Model-based Task Planning
Lin Guan*, Karthik Valmeekam*, Sarath Sreedharan, Subbarao Kambhampati
2023 NeurIPS (Benchmark) PlanBench: An Extensible Benchmark for Evaluating LLMs on Planning
Karthik Valmeekam, Matthew Marquez, Alberto Olmo, Sarath Sreedharan, Subbarao Kambhampati
2023 ICLR Relative Behavioral Attributes: Filling the Gap between Symbolic Goals and Reward Learning
Lin Guan, Karthik Valmeekam, Subbarao Kambhampati
2022 ICAPS RADAR-X: An Interactive Interface Pairing Contrastive Explanations with Revised Plan Suggestions
Karthik Valmeekam, Sarath Sreedharan, Sailik Sengupta, Subbarao Kambhampati