Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion Paper • 2610.34415 • Published 25 days ago • 43
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments Paper • 2610.25950 • Published about 1 month ago • 26
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments Paper • 2610.25950 • Published about 1 month ago • 26
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments Paper • 2610.25950 • Published about 1 month ago • 26
LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures Paper • 2610.04292 • Published Oct 3 • 31
LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures Paper • 2610.04292 • Published Oct 3 • 31
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI Paper • 2609.38143 • Published Sep 29 • 52 • 2
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI Paper • 2609.38143 • Published Sep 29 • 52
Rethinking On-Policy Distillation of Large Language Models II: One Training Example Paper • 2609.04172 • Published Sep 3 • 84
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Paper • 2609.03430 • Published Sep 3 • 94
Evaluating the Hidden Costs of Personalization in Large Language Models Paper • 2608.28833 • Published Aug 28 • 31
Evaluating the Hidden Costs of Personalization in Large Language Models Paper • 2608.28833 • Published Aug 28 • 31
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Paper • 2608.10299 • Published Aug 10 • 125
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models Paper • 2605.28009 • Published May 27 • 4
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses Paper • 2608.12307 • Published Aug 12 • 107
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models Paper • 2605.28009 • Published May 27 • 4
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design Paper • 2608.10299 • Published Aug 10 • 125
Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation Paper • 2607.27372 • Published Jul 29 • 18
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents Paper • 2607.18754 • Published Jul 21 • 25