Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Paper • 2606.07379 • Published • 5
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
Organizations
None yet
upvoted 2
papers 4 days ago
upvoted 4
papers 5 days ago
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Paper • 2606.06087 • Published • 62
Agents' Last Exam
Paper • 2606.05405 • Published • 335
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Paper • 2606.04391 • Published • 10
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 50
commented 2
papers 6 days ago
upvoted 7
papers 7 days ago
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
Paper • 2606.03841 • Published • 3
SePO: Self-Evolving Prompt Agent for System Prompt Optimization
Paper • 2606.04465 • Published • 5
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Paper • 2606.06473 • Published • 19
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Paper • 2606.04703 • Published • 23
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Paper • 2606.06492 • Published • 86
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Paper • 2606.07412 • Published • 12
OpenSkill: Open-World Self-Evolution for LLM Agents
Paper • 2606.06741 • Published • 27
upvoted 2
papers 11 days ago
upvoted 3
papers 13 days ago
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Paper • 2605.30723 • Published • 16
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
Paper • 2605.24202 • Published • 17
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Paper • 2606.01311 • Published • 36