Alexandre Piche

Publications

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation. Rafael Pardinas, Ehsan Kamalloo, Alexandre Piche, Dzmitry Bahdanau. At Transactions on Machine Learning Research (TMLR), 2026.

Paper Cite Code

How to Train Your LLM Web Agent: A Statistical Diagnosis. Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Thibault Le Sellier De Chezelles, Megh Thakkar, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Xue Steve Liu, Alexandre Drouin, Alexandre Piche, Alexandre Lacoste, Massimo Caccia. At Workshop at the Neural Information Processing Systems (NeurIPS), 2025.

How to Train Your LLM Web Agent: A Statistical Diagnosis. Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Thibault Le Sellier De Chezelles, Megh Thakkar, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Xue Steve Liu, Alexandre Drouin, Alexandre Piche, Alexandre Lacoste, Massimo Caccia. At Neural Information Processing Systems (NeurIPS), 2025.

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning. Ahmed Masry, Abhay Puri, Masoud Hashemi, Juan A. Rodriguez, Megh Thakkar, Khyati Mahajan, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Alexandre Piche, Dzmitry Bahdanau, Christopher Pal, David Vazquez, Enamul Hoque Prince , Perouz Taslakian, Sai Rajeswar Mudumba, Spandana Gella. At Conference on Language Modeling (COLM), 2025.

Paper Cite Code Video

LLMs can learn self-restraint through iterative self-reflection. Alexandre Piche, Aristides Milios, Dzmitry Bahdanau, Christopher Pal. At Transactions on Machine Learning Research (TMLR), 2025.

Paper Cite Video

How to Train Your LLM Web Agent: A Statistical Diagnosis (Oral). Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza, Hadi Nekoei, Thibault Le Sellier De Chezelles, Megh Thakkar, Nicolas Gontier, Miguel Muñoz-Mármol, Sahar Omidi Shayegan, Stefania Raimondo, Xue Steve Liu, Alexandre Drouin, Alexandre Piche, Alexandre Lacoste, Massimo Caccia. At Workshop at the International Conference of Machine Learning (ICML), 2025.

AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents. Megh Thakkar, Léo Boisvert, Thibault Le Sellier De Chezelles, Alexandre Piche, Maxime Gasse, Alexandre Lacoste, Massimo Caccia. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

Fine-Tuning Web Agents: It Works, But It's Trickier Than You Think. Massimo Caccia, Megh Thakkar, Léo Boisvert, Thibault Le Sellier De Chezelles, Alexandre Piche, Nicolas Chapados, Alexandre Drouin, Maxime Gasse, Alexandre Lacoste. At Workshop at the Neural Information Processing Systems (NeurIPS), 2024.

Exploring validation metrics for offline model-based optimisation with diffusion models. Christopher Beckham, Alexandre Piche, David Vazquez, Christopher Pal. At Transactions on Machine Learning Research (TMLR), 2024.

Paper Cite Code

Self-evaluation and self-prompting to improve the reliability of LLMs. Alexandre Piche, Aristides Milios, Dzmitry Bahdanau, Christopher Pal. At Workshop at the International Conference of Learning Representation (ICLR), 2024.

Paper Cite Video

TapeAgents: a Holistic Framework for Agent Development and Optimization. Dzmitry Bahdanau, Nicolas Gontier, Gabriel Huang, Ehsan Kamalloo, Rafael Pardinas, Alexandre Piche, Torsten Scholak, Oleh Shliazhko, Jordan Prince Tremblay, Karam Ghanem, Soham Parikh, Mitul Tiwari, Quaizar Vohra. At ArXiv, 2024.

Paper Cite Code Video

Bridging the Gap Between Target Networks and Functional Regularization. Alexandre Piche, Valentin Thomas, Joseph Marino, Gian Maria Marconi, Mohammad Emtiyaz Khan, Christopher Pal. At Transactions on Machine Learning Research (TMLR), 2023.

Paper Cite Code

Causal Discovery with Language Models as Imperfect Experts. Stephanie Long, Alexandre Piche, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin. At Workshop on Structured Probabilistic Inference & Generative Modeling (ICML), 2023.

Paper Cite Code Slides Video

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels. Sai Rajeswar Mudumba, Pietro Mazzaglia, Tim Verbelen, Alexandre Piche, Bart Dhoedt, Aaron Courville, Alexandre Lacoste. At International Conference on Machine Learning (ICML), 2023.

Paper Cite Code

Leveraging Human Preferences to Master Poetry. Rafael Pardinas, Gabriel Huang, David Vazquez, Alexandre Piche. At AAAI Workshops, 2023.

Can large language models build causal graphs?. Tibor Schuster, Stephanie Long, Alexandre Piche. At Workshop at the Neural Information Processing Systems (NeurIPS), 2022.

Paper Cite Code

Implicit Offline Reinforcement Learning via Supervised Learning. Alexandre Piche, Rafael Pardinas, David Vazquez, Igor Mordatch, Christopher Pal. At Workshop at the Neural Information Processing Systems (NeurIPS), 2022.

Paper Cite Code

Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels. Sai Rajeswar Mudumba, Pietro Mazzaglia, Tim Verbelen, Alexandre Piche, Aaron Courville, Alexandre Lacoste. At Workshop at the International Conference on Machine Learning (ICML), 2022.

Paper Cite Code

A Probabilistic Perspective on Reinforcement Learning via Supervised Learning. Alexandre Piche, Rafael Pardinas, David Vazquez, Christopher Pal. At Workshop at the International Conference on Learning Representations (ICLR), 2022.

Paper Cite Code

Planning with Latent SImulated Trajectories. Alexandre Piche, Valentin Thomas, Cyril Ibrahim, Julien Cornebise, Christopher Pal. At Workshop at the International Conference on Learning Representations (ICLR), 2019.

Probabilistic Planning with Sequential Monte Carlo Methods. Alexandre Piche, Valentin Thomas, Cyril Ibrahim, Yoshua Bengio, Christopher Pal. At International Conference on Learning Representations (ICLR), 2019.