M Saad Salman

MSS444's activity

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

upvoted 6 papers 5 days ago

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published 11 days ago • 45

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 9 days ago • 108

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 22 days ago • 115

GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills

Paper • 2609.21749 • Published 8 days ago • 18

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 12 days ago • 152

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 8 days ago • 131

upvoted 2 papers 8 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published 9 days ago • 130

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 9 days ago • 85

upvoted 2 papers 9 days ago

HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

Paper • 2609.15938 • Published 12 days ago • 31

Agora: Git as Shared Memory for Collective AutoResearch

Paper • 2609.18094 • Published 10 days ago • 57

upvoted a paper 10 days ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 16 days ago • 46

upvoted 6 papers 15 days ago

Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models

Paper • 2609.05779 • Published 21 days ago • 9

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Paper • 2609.08572 • Published 18 days ago • 107

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 28 days ago • 478

An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

Paper • 2609.10712 • Published 17 days ago • 44

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published 19 days ago • 146

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Paper • 2609.05903 • Published 21 days ago • 65

upvoted a paper 16 days ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published 19 days ago • 23

upvoted a paper 17 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 18 days ago • 174

upvoted a paper 18 days ago

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

Paper • 2609.04061 • Published 23 days ago • 9