EnvHarness: Awakening Static Worlds for Agent Learning Paper • 2608.19880 • Published 13 days ago • 273
KKHYA/llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-2of4-imp-replay-sd3_20260812_063339 Text Generation • 4B • Updated 20 days ago • 115 • 1
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis Paper • 2607.27146 • Published Jul 29 • 30
Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models Paper • 2607.05803 • Published Jul 7 • 10
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction Paper • 2606.29445 • Published Jun 28 • 28
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction Paper • 2606.28186 • Published Jun 26 • 9
A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems Paper • 2606.00138 • Published May 28 • 6
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253