siyeng feng

siyengfeng's activity

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

upvoted 2 papers 1 day ago

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

Paper • 2607.23802 • Published 16 days ago • 104

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 6 days ago • 228

upvoted 2 papers 3 days ago

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 5 days ago • 33

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 5 days ago • 88

upvoted 6 papers 4 days ago

Self-Evolving Coding Agents

Paper • 2608.03392 • Published 7 days ago • 6

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Paper • 2607.28048 • Published 7 days ago • 11

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Paper • 2608.03764 • Published 7 days ago • 25

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Paper • 2608.05139 • Published 6 days ago • 26

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 7 days ago • 34

ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment

Paper • 2608.05102 • Published 6 days ago • 64

upvoted 5 papers 5 days ago

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Paper • 2608.03874 • Published 7 days ago • 14

ExplainBench: Evaluating Code Explanations from Agents

Paper • 2607.26451 • Published 13 days ago • 13

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 7 days ago • 23

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Paper • 2608.04003 • Published 7 days ago • 33

MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations

Paper • 2607.28956 • Published 11 days ago • 96

upvoted 5 papers 6 days ago

Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures

Paper • 2607.28802 • Published 12 days ago • 10

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

Paper • 2608.02499 • Published 8 days ago • 24

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published 8 days ago • 31

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 8 days ago • 58

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 8 days ago • 165