collaborators

21 papers

cs.CL2026

SHERLOC: Structured Diagnostic Localization for Code Repair Agents

Hovhannes Tamoyan, Sean Narenthiran, Erik Arakelyan +2

LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have…

cs.SE2026

Open-SWE-Traces: Advancing Dual-Mode Multilingual Distillation for Software Engineering Agents

Wasi Uddin Ahmad, Nikolai Ludwig, Somshubra Majumdar +1

The path toward autonomous software engineering is currently bottlenecked by a severe deficit of diverse, large-scale trajectory data. We address this by introducing \ourdataset, a…

cs.CL2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman +571

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…

cs.AI2026

Workspace Optimization: How to Train Your Agent

Elad Sarafian, Gal Kaplun, Ron Banner +2

Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured externa…

cs.LG2026

Retrieval from Within: An Intrinsic Capability of Attention-Based Models

Elad Hoffer, Yochai Blau, Edan Kinderman +3

Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decoder can instead retrieve directly…

cs.SE2026

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

Nikolai Ludwig, Wasi Uddin Ahmad, Somshubra Majumdar +1

We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight frontier LLMs. Our pipeline replaces resourc…