Dheeraj Vattikonda

Privileged Information Distillation for Language Models

Nicolas Gontier

Alexandre Lacoste

Massimo Caccia

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful too… (see more)l for reinforcement learning in hard, long-horizon settings. However, transferring capabilities learned with PI to policies that must act without it at inference time remains a fundamental challenge. We study this problem in the context of distilling frontier models for multi-turn agentic environments, which typically hide their internal reasoning and expose only action trajectories. This breaks standard distillation pipelines, since successful behavior is observable, but the reasoning process is not. For this, we introduce {\pi}-Distill, a joint teacher-student objective that trains a PI-conditioned teacher and an unconditioned student simultaneously using the same model. Additionally, we also introduce On-Policy Self-Distillation (OPSD), an alternative approach that trains using Reinforcement Learning (RL) with a reverse KL-penalty between the student and the PI-conditioned teacher. We show that both of these algorithms effectively distill frontier agents using action-only PI. Specifically, we find that {\pi}-Distill and, in some cases, OPSD, outperform industry standard practices (Supervised finetuning followed by RL) that assume access to full Chain-of-Thought supervision across multiple agentic benchmarks, models, and forms of PI. We complement our results with extensive analysis that characterizes the factors enabling effective learning with PI, focusing primarily on {\pi}-Distill and characterizing when OPSD is competitive.

2026-04-29

International Conference on Machine Learning (accepted)

doi.org

openreview.net

How to Train Your LLM Web Agent: A Statistical Diagnosis

Dheeraj Vattikonda

Santhoshi Ravichandran

Emiliano Penaloza

Hadi Nekoei

Megh Thakkar

Thibault Le Sellier De Chezelles

Nicolas Gontier

Miguel Muñoz-Mármol

Sahar Omidi Shayegan

Stefania Raimondo

Xue Liu

Alexandre Drouin

Laurent Charlin

Alexandre Piché

Alexandre Lacoste

Massimo Caccia

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with op… (see more)en-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on single-step tasks that overlooks the complexity of multi-step web interactions; and second, the high compute costs required to post-train LLM-based web agents. To address this, we present the first statistically grounded study on compute allocation for LLM web-agent post-training. Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via supervised fine-tuning (SFT), followed by on-policy reinforcement learning. We find this process highly sensitive to hyperparameter choices, making exhaustive sweeps impractical. To spare others from expensive trial-and-error, we sample 1,370 configurations and use bootstrapping to estimate effective hyperparameters. Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++. Further, this strategy requires only 55% of the compute to match the peak performance of pure SFT on MiniWob++, effectively pushing the compute-performance Pareto frontier, and is the only strategy that can close the gap with closed-source models.

2025-12-02

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Learning Action and Reasoning-Centric Image Editing from Videos and Simulations

Varun Jampani

Christopher Pal