siyeng feng

siyengfeng's activity

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

upvoted 5 papers about 5 hours ago

ReFreeKV: Towards Threshold-Free KV Cache Compression

Paper • 2502.16886 • Published 5 days ago • 42

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published 8 days ago • 23

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

Paper • 2606.28480 • Published 5 days ago • 42

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

Paper • 2606.30616 • Published 1 day ago • 64

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

Paper • 2606.28733 • Published 4 days ago • 113

upvoted 3 papers 4 days ago

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

Paper • 2606.16613 • Published 16 days ago • 9

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published 7 days ago • 45

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published 6 days ago • 51

upvoted a paper 5 days ago

Are We Ready For An Agent-Native Memory System?

Paper • 2606.24775 • Published 8 days ago • 119

upvoted 2 papers 6 days ago

OpenThoughts-Agent: Data Recipes for Agentic Models

Paper • 2606.24855 • Published 8 days ago • 46

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published 8 days ago • 141

upvoted 7 papers 7 days ago

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

Paper • 2606.18844 • Published 14 days ago • 18

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

Paper • 2606.23654 • Published 9 days ago • 78

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Paper • 2606.22388 • Published 10 days ago • 95

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Paper • 2606.21649 • Published 12 days ago • 32

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Paper • 2606.20636 • Published 29 days ago • 20

Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

Paper • 2606.11897 • Published 21 days ago • 11

Self-Compacting Language Model Agents

Paper • 2606.23525 • Published 9 days ago • 18

upvoted 2 papers 18 days ago

Recursive Agent Optimization

Paper • 2605.06639 • Published May 7 • 1

Natural-Language Agent Harnesses

Paper • 2603.25723 • Published Mar 26 • 27