Hao Peng

Wesleythu's activity

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

upvoted a paper 11 days ago

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

Paper • 2606.13662 • Published 12 days ago • 27

upvoted a paper 19 days ago

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

Paper • 2606.04923 • Published 20 days ago • 40

upvoted a paper 22 days ago

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Paper • 2605.31584 • Published 25 days ago • 42

upvoted a paper 3 months ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 60

upvoted a paper 4 months ago

WildReward: Learning Reward Models from In-the-Wild Human Interactions

Paper • 2602.08829 • Published Feb 9 • 3

upvoted a collection 5 months ago

WildReward

Collection

Learning Reward Models from In-the-Wild Interactions • 4 items • Updated Mar 2 • 2

upvoted a paper 5 months ago

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Paper • 2601.06021 • Published Jan 9 • 48

upvoted a paper 8 months ago

Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models

Paper • 2510.11683 • Published Oct 13, 2025 • 16

upvoted a paper 9 months ago

DeepPrune: Parallel Scaling without Inter-trace Redundancy

Paper • 2510.08483 • Published Oct 9, 2025 • 24

upvoted a paper 10 months ago

Thyme: Think Beyond Images

Paper • 2508.11630 • Published Aug 15, 2025 • 81

upvoted a paper 11 months ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published Aug 8, 2025 • 212

upvoted a paper 12 months ago

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

Paper • 2506.18841 • Published Jun 23, 2025 • 57

upvoted 4 papers about 1 year ago

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following

Paper • 2506.09942 • Published Jun 11, 2025 • 5

MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos

Paper • 2506.04141 • Published Jun 4, 2025 • 31

AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios

Paper • 2505.16944 • Published May 22, 2025 • 8

AdaptThink: Reasoning Models Can Learn When to Think

Paper • 2505.13417 • Published May 19, 2025 • 83

upvoted 3 papers over 1 year ago

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

Paper • 2502.19328 • Published Feb 26, 2025 • 23

Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament

Paper • 2501.13007 • Published Jan 22, 2025 • 19

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Paper • 2412.15204 • Published Dec 19, 2024 • 39

upvoted a collection over 1 year ago

Crab

Collection

《Constraint Back-translation Improves Complex Instruction Following of Large Language Models》 • 6 items • Updated Mar 2 • 4