Upasana Biswas

PhD student, SCAI, Arizona State University

Joined

May 2023

Names

Upasana Biswas (Preferred)

Emails

****@asu.edu (Confirmed)

Personal Links

Google Scholar

Semantic Scholar

Career & Education History

PhD student

SCAI, Arizona State University (asu.edu)

2023 – 2028

MS student

SCAI, Arizona State University (asu.edu)

2021 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Subbarao Kambhampati

Present

Expertise

No areas of expertise listed

Publications

Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Subbarao Kambhampati, Kaya Stechly, Karthik Valmeekam, Lucas Paul Saldyt, Siddhant Bhambri, Vardhan Palod, Atharva Gundawar, Soumya Rani Samineni, Durgesh Kalwar, Upasana Biswas
- CogInterp @ NeurIPS 2025 Poster
- Readers: Everyone
Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Subbarao Kambhampati, Kaya Stechly, Karthik Valmeekam, Lucas Paul Saldyt, Siddhant Bhambri, Vardhan Palod, Atharva Gundawar, Soumya Rani Samineni, Durgesh Kalwar, Upasana Biswas
- LAW
- Readers: Everyone
Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
Siddhant Bhambri, Upasana Biswas, Subbarao Kambhampati
- LAW
- Readers: Everyone
Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?
Siddhant Bhambri, Upasana Biswas, Subbarao Kambhampati
- CogInterp @ NeurIPS 2025 Poster
- Readers: Everyone
Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation
Siddhant Bhambri, Upasana Biswas, Subbarao Kambhampati
- CogInterp @ NeurIPS 2025 Poster
- Readers: Everyone
Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Zero-Shot Cooperation in Teams
Upasana Biswas, Vardhan Palod, Siddhant Bhambri, Subbarao Kambhampati
- CoCoMARL 2025 Oral
- Readers: Everyone
Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Cooperation in Human-AI Teaming
Upasana Biswas, Siddhant Bhambri, Subbarao Kambhampati
- CoRR 2025
- Readers: Everyone
On the Pitfalls of Learning to Cooperate with Self Play Agents Checkpointed to Capture Humans of Diverse Skill Levels
Upasana Biswas, Lin Guan, Subbarao Kambhampati
- HRI (Companion) 2024
- Readers: Everyone
Hierarchical Reinforcement Learning for Ad Hoc Teaming
Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Upasana Biswas, Katharina Kann, Alessandro Roncone
- AAMAS 2023
- Readers: Everyone