1

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs

SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

Uncertainty estimation is essential for the trustworthy deployment of LLMs: it underpins self-refinement and serves as a decision signal for downstream systems, from verifiers to collaborating agents. However, existing approaches operate at …

StaRPO: Stability-Augmented Reinforcement Policy Optimization

Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the internal …

PADFormer: Pose-Agnostic Anomaly Detection from Sparse View Images

Multi-agent-as-judge: Aligning LLM-agent-based automated evaluation with multi-dimensional human evaluation

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data

LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning

On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration

Striking a Balance: Evaluating How Aggregations of Multiple Forecasts Impact Judgment Under Uncertainty

With the growing availability of quantitative forecasts from various sources, effectively communicating these multiple forecasts has become increasingly crucial. Recent advances have explored using Multiple-Forecast Visualizations (MFVs) to display …