Can Computation from Earlier Problems Help LLMs Solve New Ones? Paper • 2609.39394 • Published 7 days ago • 8
Can Computation from Earlier Problems Help LLMs Solve New Ones? Paper • 2609.39394 • Published 7 days ago • 8
Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 14 days ago • 43
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models Paper • 2608.03457 • Published Aug 4 • 35
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning Paper • 2608.04007 • Published Aug 4 • 20
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published Jun 10 • 80
Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation Paper • 2605.29861 • Published May 28 • 11
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence Paper • 2604.18292 • Published Apr 20 • 91
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence Paper • 2604.18292 • Published Apr 20 • 91
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents Paper • 2603.14465 • Published Mar 15 • 23
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning Paper • 2603.03379 • Published Mar 3 • 32
LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model Paper • 2603.01068 • Published Mar 1 • 22
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use Paper • 2510.27363 • Published Oct 31, 2025 • 23