Aakash Kumar Agarwal — accepted AI-conference papers

2026

Hypothesis-Driven Reasoning for Large Language Models

AAAI 2026technical

This paper tackles the fundamental failure of Large Language Models (LLMs) to solve new tasks when prompted with a sufficient, yet overly complex, set of multi-modal episodes. This failure stems from the model

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

ReDepress: A Cognitive Framework for Detecting Depression Relapse from Social Media

Aakash Kumar Agarwal, Saprativa Bhattacharjee, Mauli Rastogi, Jemima S. Jacob, Biplab Banerjee, Rashmi Gupta +1

EMNLP 2025

Almost 50% depression patients face the risk of going into relapse. The risk increases to 80% after the second episode of depression. Although, depression detection from social media has attained considerable attention, depression relapse detection has remained largely unexplored due to the lack of

Cited by 0 Source ↗PDF ↗Scholar ↗