Papers

• ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents

  Arizona State University

  Published on: 2026-01-18 1 author
• RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

  Temple University

  Published on: 2026-01-05 1 author
• A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm

  Vanderbilt University

  Published on: 2025-07-12 1 author
• SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization

  Vanderbilt University

  Published on: 2025-07-12 1 author
• The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs

  Published on: 2025-06-13 1 author
• Transaction Categorization with Relational Deep Learning in QuickBooks

  University of Notre Dame

  Published on: 2025-06-10 1 author
• Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation

  University of California

  Published on: 2025-06-07 1 author
• Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

  Virginia Tech

  Published on: 2025-06-07 1 author
• Learning to Search Effective Example Sequences for In-Context Learning

  Published on: 2025-03-11 1 author
• Towards Statistical Factuality Guarantee for Large Vision-Language Models

  Vanderbilt University

  Published on: 2025-02-27 1 author
• HyQE: Ranking Contexts with Hypothetical Query Embeddings

  Boston University

  Published on: 2024-10-20 1 author
• Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution

  Published on: 2024-10-12 1 author
• Data-Driven Discovery of Conservation Laws from Trajectories via Neural Deflation

  University of Massachusetts Amherst

  Published on: 2024-10-07 1 author
• SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models

  Published on: 2024-03-04 1 author
• SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency

  Vanderbilt University

  Published on: 2024-02-18 1 author
• Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

  Vanderbilt University

  Published on: 2024-01-12 1 author
• Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

  Vanderbilt University

  Published on: 2023-10-31 1 author