EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery Paper • 2606.13662 • Published 16 days ago • 28
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards Paper • 2605.31584 • Published 29 days ago • 43
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse Paper • 2603.12201 • Published Mar 12 • 60
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units Paper • 2601.21996 • Published Jan 29 • 5
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards Paper • 2601.06021 • Published Jan 9 • 48
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI Paper • 2512.16676 • Published Dec 18, 2025 • 224
Glyph: Scaling Context Windows via Visual-Text Compression Paper • 2510.17800 • Published Oct 20, 2025 • 69
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models Paper • 2510.11683 • Published Oct 13, 2025 • 16
DeepPrune: Parallel Scaling without Inter-trace Redundancy Paper • 2510.08483 • Published Oct 9, 2025 • 24