Jingcheng Liang

leoleung04's activity

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

upvoted a paper 3 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 12 days ago • 39

upvoted a paper 6 days ago

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

Paper • 2610.32285 • Published 10 days ago • 54

upvoted a paper 14 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 18 days ago • 165

upvoted a paper 17 days ago

Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL

Paper • 2610.21439 • Published 18 days ago • 35

upvoted 2 papers about 1 month ago

Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL

Paper • 2610.00574 • Published Sep 30 • 34

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published Sep 30 • 94

upvoted a paper 2 months ago

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

Paper • 2608.28122 • Published Aug 28 • 65

upvoted 4 papers 3 months ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published Aug 7 • 81

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published Jul 22 • 23

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

Paper • 2607.21461 • Published Jul 23 • 96

From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality

Paper • 2607.13196 • Published Jul 14 • 26

upvoted 3 papers 4 months ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 105

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published Jul 9 • 73

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 43

upvoted a paper 5 months ago

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

upvoted a paper 6 months ago

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL

Paper • 2604.17073 • Published Apr 18 • 9

upvoted 2 papers 7 months ago

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

Paper • 2604.08865 • Published Apr 10 • 29

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published Apr 12 • 27