siyeng feng

siyengfeng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 17 days ago

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Paper • 2608.27454 • Published 19 days ago • 33

upvoted a paper 19 days ago

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 22 days ago • 207

upvoted 3 papers 24 days ago

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published 26 days ago • 66

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Paper • 2608.18580 • Published 27 days ago • 121

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 26 days ago • 275

upvoted 4 papers 26 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published Aug 14 • 170

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published Aug 15 • 446

Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

Paper • 2608.15669 • Published about 1 month ago • 63

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 29 days ago • 151

upvoted 11 papers about 1 month ago

Intern-S2-Preview: Scientific Agentic Foundation Model

Paper • 2608.13505 • Published Aug 13 • 72

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published Aug 13 • 63

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published Aug 7 • 111

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published Jul 31 • 113

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 219

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 779

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published Aug 10 • 18

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 119

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Paper • 2608.08311 • Published Aug 8 • 92

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published Aug 10 • 343

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Paper • 2608.09802 • Published Aug 10 • 136