5 papers
A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering
Yun-Shiuan Chuang, Yirou Ge, Yixi Li +6
A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compresses its library, even when…
CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning
Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao +8
Direct Preference Optimization (DPO) treats all constraint violations equally: a 1,000 overshoot induce the same training signal. It is also susceptible…
Ada-RS: Adaptive Rejection Sampling for Selective Thinking
Yirou Ge, Yixi Li, Alec Chiu +8
Large language models (LLMs) are increasingly being deployed in cost and latency-sensitive settings. While chain-of-thought improves reasoning, it can waste tokens on simple reques…
Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents
Yun-Shiuan Chuang, Chaitanya Kulkarni, Alec Chiu +8
Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must bo…
NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
Sudhanshu Garg, Andrew Wang, Chaitanya Kulkarni +11
We present the development and optimization of PayPal's Commerce Agent, powered by NEMO-4-PAYPAL, a multi-agent system designed to revolutionize agentic commerce on the PayPal plat…