activity
20242026
collaborators

5 papers

cs.AI2026

CUBE: A Standard for Unifying Agent Benchmarks

Alexandre Lacoste, Nicolas Gontier, Oleh Shliazhko +23

The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating…

cs.LG2026

Privileged Information Distillation for Language Models

Emiliano Penaloza, Dheeraj Vattikonda, Nicolas Gontier +3

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, lo…

cs.AI2026

How to Train Your LLM Web Agent: A Statistical Diagnosis

Dheeraj Vattikonda, Santhoshi Ravichandran, Emiliano Penaloza +13

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has bee…

cs.AI2025

Self-Evolving Curriculum for LLM Reasoning

Xiaoyin Chen, Jiarui Lu, Minsu Kim +6

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and…

cs.AI2024

TapeAgents: a Holistic Framework for Agent Development and Optimization

Dzmitry Bahdanau, Nicolas Gontier, Gabriel Huang +10

We present TapeAgents, an agent framework built around a granular, structured log tape of the agent session that also plays the role of the session's resumable state. In TapeAgents…