Shuang Sun

SNHE's activity

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

upvoted a paper 18 days ago

Harness Scaling for Generalizable Agentic Reinforcement Learning

Paper • 2610.29458 • Published 19 days ago • 16

upvoted a paper 26 days ago

Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards

Paper • 2610.16533 • Published 28 days ago • 10

upvoted a paper 28 days ago

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

Paper • 2610.13395 • Published Oct 9 • 45

upvoted a paper 30 days ago

Foundations of Large Language Models

Paper • 2501.09223 • Published Oct 8 • 42

upvoted a paper about 2 months ago

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Paper • 2609.28416 • Published Sep 23 • 26

upvoted 4 papers 3 months ago

ClawGym II: Exploring Black-Box RL on Agent Harness

Paper • 2608.16798 • Published Aug 17 • 42

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published Aug 10 • 18

CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Paper • 2608.06352 • Published Aug 6 • 15

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 525

upvoted 2 papers 4 months ago

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published Jul 23 • 93

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Paper • 2607.12395 • Published Jul 14 • 91

upvoted 3 papers 5 months ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 163

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Paper • 2606.12087 • Published Jun 10 • 50

DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch

Paper • 2606.10728 • Published Jun 9 • 38

upvoted 2 papers 6 months ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published May 3 • 125

ClawGym: A Scalable Framework for Building Effective Claw Agents

Paper • 2604.26904 • Published Apr 29 • 56

upvoted a paper 8 months ago

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

Paper • 2603.03194 • Published Mar 3 • 55

upvoted a collection 8 months ago

SWE Agent Series

Collection

Models trained by SWE-Master and SWE-World, including both policy models and verifiers. • 13 items • Updated Mar 23 • 4

upvoted 2 papers 9 months ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Paper • 2602.03411 • Published Feb 3 • 39

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published Feb 3 • 42