arXiv Computer Science @arxiv_cs@qoto.org

From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG https://arxiv.org/abs/2603.03292 #cs.CL #cs.AI #cs.IR

SE-Search: Self-Evolving Search Agent via Memory and Dense Reward https://arxiv.org/abs/2603.03293 #cs.CL

Fine-Tuning and Evaluating Conversational AI for Agricultural Advisory https://arxiv.org/abs/2603.03294 #cs.CL #cs.AI #cs.LG

Language Model Goal Selection Differs from Humans' in an Open-Ended Task https://arxiv.org/abs/2603.03295 #cs.CL #cs.AI #cs.CY

PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents https://arxiv.org/abs/2603.03296 #cs.CL #cs.AI #cs.IR

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement https://arxiv.org/abs/2603.03297 #cs.CL #cs.AI #cs.LG

TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation https://arxiv.org/abs/2603.03298 #cs.CL #cs.AI

GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning https://arxiv.org/abs/2603.02212 #cs.DB #cs.AI

A Zipf-preserving, long-range correlated surrogate for written language and other symbolic sequences https://arxiv.org/abs/2603.02213 #cond-mat.stat-mech #q-bio.GN #cs.CL

Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving https://arxiv.org/abs/2603.02214 #cs.AI #cs.CR #cs.LG

RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning https://arxiv.org/abs/2603.02215 #cs.LG #cs.AI

ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue https://arxiv.org/abs/2603.02216 #cs.LG #cs.AI

Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression https://arxiv.org/abs/2603.02217 #cs.LG #cs.AI

Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain https://arxiv.org/abs/2603.02218 #math.IT #cs.LG #cs.AI #cs.CL #cs.IT

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels https://arxiv.org/abs/2603.02219 #cs.LG #cs.AI

Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting https://arxiv.org/abs/2603.02220 #cs.LG #cs.AI #cs.CV

MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction https://arxiv.org/abs/2603.02221 #cs.LG #cs.AI

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation https://arxiv.org/abs/2603.00546 #cs.AI #cs.CV

PM2Lat: Highly Accurate and Generalized Prediction of DNN Execution Latency on GPUs https://arxiv.org/abs/2603.00549 #cs.PF

Serendipity with Generative AI: Repurposing knowledge components during polycrisis with a Viable Systems Model approach https://arxiv.org/abs/2602.23365 #cs.HC #cs.CL #cs.IR