Kaya Stechly
- Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
2025/05/19 by Karthik Valmeekam, Vardhan Palod, Valmeekam, Karthik +7 · 26 voices · 18 citations
#cs.LG #cs.AI
- Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
2025/04/14 by Subbarao Kambhampati, Kambhampati, Subbarao, Karthik Valmeekam +16 · 17 voices · 14 citations
Computer Science · Psychology · #Intelligent Tutoring Systems and Adaptive Learning #Innovative Teaching and Learning Methods #Topic Modeling
- LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
2024/09/20 by Karthik Valmeekam, Valmeekam, Karthik, Kaya Stechly +3 · 6 voices · 20 citations
#cs.AI #cs.CL
- Chain of Thoughtlessness? An Analysis of CoT in Planning
2024/05/08 by Kaya Stechly, Stechly, Kaya, Karthik Valmeekam +3 · 23 citations
Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Educational Tools and Methods #FOS: Computer and information sciences #Innovative Teaching and Learning Methods
- On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks
2024/02/12 by Kaya Stechly, Karthik Valmeekam, Stechly, Kaya +3 · 18 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems
2023/10/19 by Kaya Stechly, Stechly, Kaya, Matthew Marquez +3 · 6 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
2024/10/03 by Karthik Valmeekam, Valmeekam, Karthik, Kaya Stechly +5 · 1 voice · 4 citations
Engineering · #BIM and Construction Integration #cs.AI