siyeng feng

siyengfeng's activity

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

upvoted 3 papers 3 days ago

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

Paper • 2608.19799 • Published 4 days ago • 61

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

Paper • 2608.18580 • Published 5 days ago • 114

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 4 days ago • 256

upvoted a paper 4 days ago

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

Paper • 2608.14036 • Published 10 days ago • 163

upvoted 3 papers 5 days ago

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

Paper • 2608.15089 • Published 9 days ago • 436

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

Paper • 2608.15669 • Published 8 days ago • 62

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

Paper • 2608.16072 • Published 7 days ago • 148

upvoted 5 papers 10 days ago

Intern-S2-Preview: Scientific Agentic Foundation Model

Paper • 2608.13505 • Published 11 days ago • 69

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

Paper • 2608.13560 • Published 11 days ago • 54

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

Paper • 2608.06867 • Published 17 days ago • 109

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published 24 days ago • 113

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 15 days ago • 217

upvoted a paper 12 days ago

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

Paper • 2608.09888 • Published 14 days ago • 712

upvoted 5 papers 13 days ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 14 days ago • 18

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 14 days ago • 113

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

Paper • 2608.08311 • Published 16 days ago • 90

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

Paper • 2608.09819 • Published 14 days ago • 338

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

Paper • 2608.09802 • Published 14 days ago • 133

upvoted 2 papers 15 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 29 days ago • 106

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 17 days ago • 247