6 papers
Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting
Elias Lumer, Sahil Sen, Vamse Kumar Subbiah +1
Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual t…
Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?
Nishanth Nayakanti, Prasang Gupta, Ashutosh Bilthare +1
In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than recording the decision. We measu…
Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution
Ethan Leung, Elias Lumer, Corey Feld +3
Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trus…
Recursive Agent Harnesses
Elias Lumer, Sahil Sen, Kevin Paul +1
Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code t…
Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing
Anmol Gulati, Sahil Sen, Waqar Sarguroh +1
Recent advances in multimodal Retrieval-Augmented Generation (RAG) enable Large Language Models (LLMs) to analyze enterprise spreadsheet workbooks containing millions of cells, cro…
From Rows to Reasoning: A Retrieval-Augmented Multimodal Framework for Spreadsheet Understanding
Anmol Gulati, Sahil Sen, Waqar Sarguroh +1
Large Language Models (LLMs) struggle to reason over large-scale enterprise spreadsheets containing thousands of numeric rows, multiple linked sheets, and embedded visual content s…