collaborators

5 papers

cs.AI2026

SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents

Vivek Kulkarni, Sudipta Paul, Aounon Kumar +2

Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time. Recently, methods like…

cs.AI2026

Search-GRT: Guided Retrieval Training of Search Agents to Optimize for Complex Question Answering

Aounon Kumar, Sudipta Paul, Vivek Kulkarni +2

The effective use of search engines by large language models (LLMs) remains a significant challenge, particularly in complex, multi-hop question-answering (MHQA) tasks. These tasks…

cs.AI2026

PROGRESS: Coverage-guided RL to Train Search-augmented LLM Agent

Sudipta Paul, Vijay Srinivasan, Vivek Kulkarni +4

Existing search-augmented LLM agents are trained using Reinforcement Learning to boost its reasoning capabilities. However, these approaches primarily rely on outcome-level rewards…

cs.AI2026

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

Tianyu Yang, Sudipta Paul, Vijay Srinivasan +2

Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents active…

cs.CV2025

LINGUAL: Language-INtegrated GUidance in Active Learning for Medical Image Segmentation

Md Shazid Islam, Shreyangshu Bera, Sudipta Paul +1

Although active learning (AL) in segmentation tasks enables experts to annotate selected regions of interest (ROIs) instead of entire images, it remains highly challenging, labor-i…