Salesforce Koa: An Enterprise Language Model for Agentic Tool Use

arXiv:2609.15066 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-14

Updated: 2026-10-08

Comments: 16 pages, 4 figures, 5 tables

Code: https://github.com/NVIDIA-NeMo/Automodel

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 13× in this paper · explained in 2 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• Foundation Model — 11× in this paper · explained in 3 episodes
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Foundation Models — 5× in this paper · explained in 7 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Agentic Task — 4× in this paper · explained in 1 episode
• Agentic Tasks — 4× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Group Relative Policy Optimization — 3× in this paper
• Group Relative Policy Optimization (GRPO) — 3× in this paper · explained in 5 episodes
• Agentic Reasoning — 2× in this paper · explained in 1 episode
• Customer Relationship Management — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Activation Checkpointing — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Berkeley Function Calling Leaderboard — 1× in this paper
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• Gemma 3 Technical Report
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Mistral 7B
• APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets
• On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training
• Nemotron-4 340B Technical Report
• APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
• Qwen2 Technical Report
• PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering