Kalman Delta Networks: Uncertainty-aware Associative Memory Paper • 2609.07816 • Published Sep 7 • 17
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction Paper • 2605.09649 • Published May 10 • 13
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems Paper • 2605.04018 • Published May 5 • 27
QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs Paper • 2602.20629 • Published Feb 24 • 5
ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution Paper • 2603.02510 • Published Mar 3 • 3
QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs Paper • 2602.20629 • Published Feb 24 • 5
ResearchGym: Evaluating Language Model Agents on Real-World AI Research Paper • 2602.15112 • Published Feb 16 • 22
Multi-LLM Thematic Analysis with Dual Reliability Metrics: Combining Cohen's Kappa and Semantic Similarity for Qualitative Research Validation Paper • 2512.20352 • Published Dec 23, 2025 • 3
Prompt Cache: Modular Attention Reuse for Low-Latency Inference Paper • 2311.04934 • Published Nov 7, 2023 • 33