1 citations · 1 across the 5 of their papers we have counts for
5 papers
Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou +5
Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models. Yet, typical RLVR approaches fail on difficult problems: when a model cannot gene…
Structure Enables Effective Self-Localization of Errors in LLMs
Ankur Samanta, Akshayaa Magesh, Ayush Jain +8
Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward buildin…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Imbalanced Gradients in RL Post-Training of Multi-Task LLMs
Runzhe Wu, Ankur Samanta, Ayush Jain +7
Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assume…
Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
Ankur Samanta, Akshayaa Magesh, Runzhe Wu +7
Self-improvement, where models improve beyond their current performance without external supervision, remains a challenge. The core difficulty is sourcing a training signal stronge…