siyeng feng

siyengfeng's activity

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

upvoted 4 papers 3 days ago

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 5 days ago • 17

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Paper • 2607.01874 • Published 4 days ago • 17

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Paper • 2607.01647 • Published 4 days ago • 30

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 7 days ago • 42

upvoted a collection 4 days ago

swe-zero-to-swe-hero

Collection

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496) • 6 items • Updated 6 days ago • 6

upvoted 7 papers 5 days ago

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems

Paper • 2605.21997 • Published May 21 • 2

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Paper • 2606.30406 • Published 7 days ago • 14

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published 13 days ago • 41

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published 9 days ago • 35

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 7 days ago • 101

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 10 days ago • 106

Orca: The World is in Your Mind

Paper • 2606.30534 • Published 7 days ago • 234

upvoted 5 papers 6 days ago

ReFreeKV: Towards Threshold-Free KV Cache Compression

Paper • 2502.16886 • Published 10 days ago • 48

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published 13 days ago • 30

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Paper • 2606.28480 • Published 10 days ago • 47

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published 7 days ago • 89

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published 9 days ago • 145

upvoted 3 papers 10 days ago

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

Paper • 2606.16613 • Published 21 days ago • 9

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published 12 days ago • 47

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published 11 days ago • 54