3 papers
cs.AI2026
The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
Harshee Jignesh Shah
Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration fra…
cs.RO2025
SITCOM: Scaling Inference-Time COMpute for VLAs
Ayudh Saxena, Harsh Shah, Sandeep Routray +2
Learning robust robotic control policies remains a major challenge due to the high cost of collecting labeled data, limited generalization to unseen environments, and difficulties…
math.OC2025
Online Convex Optimization with Switching Cost with Only One Single Gradient Evaluation
Harsh Shah, Purna Chandrasekhar, Rahul Vaze
Online convex optimization with switching cost is considered under the frugal information setting where at time , before action is taken, only a single function evaluation…