Pavo
Publications

Research Papers

Deep experience in systems intelligence — autonomous agents, causal reasoning, reinforcement learning, large-scale personalization, and marketplace optimization.

01

Systems Intelligence & Autonomous Agents

Lifelong learning, multi-agent coordination, agent safety, and system ownership — the research foundations for compounding enterprise AI.

Pre-print
System Ownership as a Lifelong Learning Problem: A Formulation for Long-Horizon Software Maintenance(stealth)

P. Trochim, S. Pan, V. Chandela

Pre-print
Informational Individuality and Behavioural Consistency: A Theory Framework of Lifelong Learning for LLM Agents(stealth)

S. Pan, P. Trochim, V. Chandela, R. Mehrotra

Pre-print
Programmatic Process Rewards Improve the Reliability of Agent-Safety Reinforcement Learning(stealth)

S. Pan, R. Mehrotra

Pre-print
Mini-uber: Hold-Probe Evaluation for Multi-Regime Agent Tasks(stealth)

S. Pan, R. Mehrotra

Pre-print
Spectrum-Anchored Updates Preserve Plasticity in Continual Learning(stealth)

S. Pan, X. Guan

Pre-print
AutoGT: Distilling High Quality Evaluation Ground Truth from Heterogeneous Sources on Knowledge-Intensive Tasks(stealth)

S. Pan, S. Saket, R. Mehrotra

Pre-print
RCA Playbooks: Probabilistic Reconstruction of Diagnostic Workflows from SQL Query Graphs(stealth)

S. Saket, S. Dhar, R. Mehrotra

Pre-print
Prescriptive Cheatsheets: Structured Artifacts via Evidence-Aware Submodular Synthesis(stealth)

S. Saket, S. Dhar, R. Mehrotra

Pre-print
Semantic Factorization of Analytical SQL Workloads(stealth)

S. Saket, S. Dhar, R. Mehrotra

02

AI-Powered Engineering & Code Intelligence

Intelligent systems that understand codebases, retrieve context, and assist engineers with production-grade code recommendations.

03

Intelligent Decision Systems & Reinforcement Learning

Causal reasoning, model-based planning, and bandit optimization — algorithmic foundations for systems that learn from decisions and compound over time.

ICLR 2022

A. Byravan, L. Hasenclever, P. Trochim, M. Mirza, A. Ialongo, Y. Tassa, J. Springenberg, A. Abdolmaleki, N. Heess, J. Merel, M. Riedmiller

KDD 2020

J. McInerney, B. Brost, P. Chandar, R. Mehrotra, B. Carterette

WSDM 2024
RecSys 2018

J. McInerney, B. Lacker, S. Hansen, K. Higley, H. Bouchard, A. Gruson, R. Mehrotra

arXiv 2022 (DeepMind)

Y. Chervonyi, P. Dutta, P. Trochim, O. Voicu, C. Paduraru, C. Qian, E. Karagozler, J. Davis, R. Chippendale, G. Bajaj, S. Witherspoon, J. Luo

04

Large-Scale Personalization & Recommendation

Architecting ML systems at 100M+ user scale — embeddings, ranking, sequencing, and real-time serving across Spotify, ShareChat, and Seekho.

FIRE 2023

O. Jeunen, H. Sagtani, H. Doi, R. Karimov, N. Pokharna, D. Kalim, A. Ustimenko, C. Green, R. Mehrotra, W. Shi

CIKM 2023
RecSys 2020

C. Hansen, C. Hansen, L. Maystre, R. Mehrotra, B. Brost, F. Tomasi, M. Lalmas

WSDM 2021

C. Hansen, R. Mehrotra, C. Hansen, B. Brost, L. Maystre, M. Lalmas

05

Multi-Stakeholder Optimization & Marketplace Intelligence

Balancing competing objectives across users, creators, and platforms — fairness, multi-sided value, and system-level trade-offs.