siyeng feng

siyengfeng's activity

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

upvoted a paper about 6 hours ago

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

Paper • 2608.09888 • Published 2 days ago • 243

upvoted 5 papers about 10 hours ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 2 days ago • 10

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 2 days ago • 32

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

Paper • 2608.08311 • Published 4 days ago • 66

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

Paper • 2608.09819 • Published 2 days ago • 207

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

Paper • 2608.09802 • Published 2 days ago • 116

upvoted 2 papers 2 days ago

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

Paper • 2607.23802 • Published 17 days ago • 105

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 5 days ago • 232

upvoted 2 papers 4 days ago

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 6 days ago • 33

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 6 days ago • 90

upvoted 6 papers 5 days ago

Self-Evolving Coding Agents

Paper • 2608.03392 • Published 8 days ago • 6

SKILL-KD: Contrastive Skill Distillation for LLM Agents

Paper • 2607.28048 • Published 8 days ago • 11

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Paper • 2608.03764 • Published 8 days ago • 25

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

Paper • 2608.05139 • Published 7 days ago • 26

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 8 days ago • 34

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

Paper • 2608.05102 • Published 7 days ago • 64

upvoted 4 papers 6 days ago

ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?

Paper • 2608.03874 • Published 8 days ago • 14

ExplainBench: Evaluating Code Explanations from Agents

Paper • 2607.26451 • Published 14 days ago • 13

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 8 days ago • 23

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

Paper • 2608.04003 • Published 7 days ago • 33