Author

Swastik Roy

Observed name: Roy, Swastik

Institutions: Amazon (United States), University of Massachusetts Lowell

Observed institutions: Amazon (United States), University of Massachusetts Lowell

OpenAlex ID: A5129717881

OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning

2025 · Zhenyu Bi, Meng Lu, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · 1

PDF

Multi-LLM Collaborative Alignment via Stackelberg Games

2026 · Hahn, Christina, Feng, Shangbin, et al. · arXiv (Cornell University)

PDF

Aligned Data Can Induce Misalignment via Context Confusion

2026 · Bakman, Yavuz, Yaldiz, Duygu Nur, et al. · arXiv (Cornell University)

PDF

Attention-Aware Routing: Coupling Routing and Attention in MoEs

2026 · Kosmopoulou, Despoina, Tsetsilas, Anastasios, et al. · arXiv (Cornell University)

PDF

JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation

2026 · Zhenyu Bi, Gaurav Srivastava, et al. · Proceedings of the AAAI Conference on Artificial Intelligence

PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges

2026 · Swastik Roy, Rajkumar Pujari, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Works count: 6

Citation count: 1

H-index: 1

I10-index: