Arash Behboodi

I am a research scientist and Director of Engineering at Qualcomm AI Research, working on the theoretical foundations of information and computational systems.

My interests include information theory, learning theory, machine learning for inverse problems, compressed sensing, geometric deep learning, differentiable simulation, neural reasoning and agentic AI.

Information Theory Learning Theory Inverse Problems

View Publications Read Bio Visit Blog

News and Highlights

Recent papers, talks, and research updates.

New paper: Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards , NeurIPS Workshop CL4FMAgents, 2026
New paper: Enabling Dynamic Computation in Looped LMs
NeurIPS 2026: Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
New paper: When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
New paper: Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models and Hugging Face page
New paper on our NeurIPS 2025 demo: Efficient Reasoning on the Edge and Hugging Face page
New paper: LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
ACL Findings2026: LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents
See our NeurIPS 2025 expo demo on: Efficient Reasoning on the Edge.
New paper: Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction
I give a keynote talk about Information Theoretic Perspective on Conformal Prediction at 14th Symposium on Conformal and Probabilistic Prediction with Applications, COPA 2025

Selected Recent Papers

A quick tour through recent work across theory, reasoning, and simulation.

Tianyu Liu, Davide Belli, Bence Major, Arash Behboodi, Tribhuvanesh Orekondy Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards , NeurIPS Workshop CL4FMAgents, 2026
Aayush Mishra, Arnau Padrés Masdemont, Victor Conchello Vendrell, Jordi Ros Giralt, Arash Behboodi, Fabio Valerio Massoli, Enabling Dynamic Computation in Looped LMs, 2026
Fabio Valerio Massoli, Andrey Kuzmin, Arash Behboodi, Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck, NeurIPS 2026
Corrado Rainone, Davide Belli, Bence Major, Arash Behboodi, When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems, 2026
Victor Conchello Vendrell, Arnau Padres Masdemont, Niccolò Grillo, Jordi Ros-Giralt, Arash Behboodi, Fabio Valerio Massoli, Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models , 2026
Yelysei Bondarenko et al., Efficient Reasoning on the Edge, 2026
Gabriele Cesa, Thomas Hehn, Aleix Torres-Camps, Àlex Batlle Casellas, Jordi Ros-Giralt, Arash Behboodi, Tribhuvanesh Orekondy, LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation, 2026
Amin Rakhsha, Thomas Hehn, Pietro Mazzaglia, Fabio Valerio Massoli, Arash Behboodi, Tribhuvanesh Orekondy, LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents, ACL Findings 2026
Arash Behboodi, Alvaro H.C. Correia, Fabio Valerio Massoli, Christos Louizos, Fundamental bounds on efficiency-confidence trade-off for transductive conformal prediction, 2025

Misc.

Workshops, conversations, and related projects.

Workshop D3S3: Data-driven and Differentiable Simulations, Surrogates, and Solvers at NeurIPS 2024.
My chat with Sam Charrington at TWIML AI podcast around Differentiable Simulation, Conformal Prediction, and AI at the Edge.