ChemAmp: Amplified Chemistry Tools via Composable Agents
arXiv:2505.21569v3 Announce Type: replace-cross Abstract: Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their…
CodeTracer: Towards Traceable Agent States
arXiv:2604.11641v3 Announce Type: replace-cross Abstract: Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate…
Evaluating Supervised Machine Learning Models: Principles, Pitfalls, and Metric Selection
arXiv:2604.13882v1 Announce Type: cross Abstract: The evaluation of supervised machine learning models is a critical stage in the development of…
Beyond Conservative Automated Driving in Multi-Agent Scenarios via Coupled Model Predictive Control and Deep Reinforcement Learning
arXiv:2604.13891v1 Announce Type: cross Abstract: Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need…
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
arXiv:2604.13016v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) has become a core technique in the post-training of large language models,…
Exploration and Exploitation Errors Are Measurable for Language Model Agents
arXiv:2604.13151v1 Announce Type: new Abstract: Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding…
FCBV-Net: Category-Level Robotic Garment Smoothing via Feature-Conditioned Bimanual Value Prediction
arXiv:2508.05153v2 Announce Type: replace-cross Abstract: Category-level generalization for robotic garment manipulation, such as bimanual smoothing, remains a significant hurdle due…
Variance Computation for Weighted Model Counting with Knowledge Compilation Approach
arXiv:2601.03523v2 Announce Type: replace Abstract: One of the most important queries in knowledge compilation is weighted model counting (WMC), which…
Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents
arXiv:2604.11465v2 Announce Type: replace Abstract: Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents…