Article
GLM-5.2: Built for Long-Horizon Tasks
zai-org
• • 124
Zhihao Lin
mathieulin
AI & ML interests
None yet
Recent Activity
upvoted an article 1 day ago
GLM-5.2: Built for Long-Horizon Tasks authored a paper 2 days ago
AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches? authored a paper 2 days ago
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak ApproachOrganizations
None yet
upvoted an article 1 day ago
authored 3
papers 2 days ago
AtomicCommitBench: Can Coding Agents Reconstruct Commit Histories from Squashed Patches?
Paper • 2607.03332 • Published
PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
Paper • 2409.14177 • Published
Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs
Paper • 2305.12138 • Published
upvoted a paper 2 days ago
authored a
paper 4 days ago
upvoted a paper 7 days ago
submitted a
paper to Daily Papers 7 days ago
upvoted a paper 9 days ago
upvoted a paper 10 days ago
submitted 2
papers to Daily Papers 10 days ago
authored 3
papers 12 days ago
Executing as You Generate: Hiding Execution Latency in LLM Code Generation
Paper • 2604.00491 • Published • 6
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
Paper • 2606.26979 • Published • 3
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
Paper • 2606.26978 • Published • 4