Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving information already known) and under-search (failing to search when necessary), which leads to unnecessary overhead and unreliable outputs. Current training methods, which typically rely on outcome-based rewards in a RL framework, lack the fine-grained control needed to address these inefficiencies. To overcome this, we introduce Hierarchical Process Rewards for Efficient agentic RAG (HiPRAG), a training methodology that incorporates a fine-grained, knowledge-grounded process reward into the RL training. Our approach evaluates the necessity of each search decision on-the-fly by decomposing the agent's reasoning trajectory into discrete, parsable steps. We then apply a hierarchical reward function that provides an additional bonus based on the proportion of optimal search and non-search steps, on top of commonly used outcome and format rewards. Experiments on the Qwen2.5 and Llama-3.2 models across seven diverse QA benchmarks show that our method achieves average accuracies of 65.4% (3B) and 67.2% (7B). This is accomplished while improving search efficiency, reducing the over-search rate to just 2.3% and concurrently lowering the under-search rate. These results demonstrate the efficacy of optimizing the reasoning process itself, not just the final outcome. Further experiments and analysis demonstrate that HiPRAG shows good generalizability across a wide range of RL algorithms, model families, sizes, and types. This work demonstrates the importance and potential of fine-grained control through RL, for improving the efficiency and optimality of reasoning for search agents.

Before viewing the AI/Machine Learning Systems Engineer / Grand Prairie, TX at Lockheed Martin job, please verify that you are a human and not a robot overlord.

A 12-year-old who read The Lord Of The Rings aged five has become the youngest Cornell University freshman in the Ivy School's history. Jeremy Shuler was home-schooled by his parents - both aerospace engineers from Grand Prairie, Texas - and started reading books in English and Korean aged two. To help get him into Cornell, Jeremy's parents moved to Ithaca, where his father, Andy Shuler, took up a post at Lockheed Martin Upstate New York. A 12-year-old who started studying calculus aged 6 has become the youngest Cornell University freshman in the Ivy School's history With his bowl-cut hair, cherubic face and frequent happy laughter, Jeremy is clearly still a child despite his advanced intelligence. He swung in his chair while his parents, who he calls Mommy and Daddy, recounted his early years during an interview at the engineering school where his grandfather is a professor, his father got his doctorate and Jeremy is now an undergrad.