siyeng feng

siyengfeng's activity

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

upvoted 3 papers about 6 hours ago

Building to the Test: Coding Agents Deliver What You Check, Not What You Requested

Paper • 2606.28430 • Published Jun 26 • 9

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

Paper • 2607.00152 • Published about 1 month ago • 9

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

Paper • 2607.01211 • Published 30 days ago • 9

upvoted a paper about 7 hours ago

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

Paper • 2607.01071 • Published 30 days ago • 31

upvoted 5 papers 1 day ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published 3 days ago • 28

Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory

Paper • 2607.24368 • Published 4 days ago • 28

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

Paper • 2607.25431 • Published 3 days ago • 74

A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Paper • 2607.24223 • Published 4 days ago • 87

OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs

Paper • 2607.25669 • Published 3 days ago • 8

upvoted 5 papers 2 days ago

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

Paper • 2607.23588 • Published 5 days ago • 119

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Paper • 2607.24720 • Published 4 days ago • 25

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

Paper • 2607.22798 • Published 7 days ago • 57

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Paper • 2607.24280 • Published 4 days ago • 81

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 4 days ago • 386

liked a dataset 3 days ago

skylenage-ai/QwenClawBench

Viewer • Updated Apr 10 • 100 • 32 • 15

upvoted 4 papers 3 days ago

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

Paper • 2607.14277 • Published 16 days ago • 10

Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems

Paper • 2607.21503 • Published 8 days ago • 24

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published 9 days ago • 30

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 7 days ago • 45

upvoted a paper 6 days ago

OpenForgeRL: Train Harness-native Agents in Any Environment

Paper • 2607.21557 • Published 8 days ago • 8