M Saad Salman

MSS444's activity

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

upvoted 2 papers 3 days ago

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

Paper • 2609.20519 • Published 4 days ago • 94

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 4 days ago • 71

upvoted 2 papers 4 days ago

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

Paper • 2609.15938 • Published 7 days ago • 28

Agora: Git as Shared Memory for Collective AutoResearch

Paper • 2609.18094 • Published 5 days ago • 45

upvoted a paper 5 days ago

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

Paper • 2609.11682 • Published 11 days ago • 44

upvoted 6 papers 10 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 16 days ago • 9

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

Paper • 2609.08572 • Published 13 days ago • 103

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 23 days ago • 469

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

Paper • 2609.10712 • Published 12 days ago • 43

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

Paper • 2609.07064 • Published 14 days ago • 143

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

Paper • 2609.05903 • Published 16 days ago • 63

upvoted a paper 11 days ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published 14 days ago • 23

upvoted a paper 12 days ago

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

Paper • 2609.08183 • Published 13 days ago • 171

upvoted 3 papers 13 days ago

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

Paper • 2609.04061 • Published 18 days ago • 9

Iris: Climbing to the Search Frontier

Paper • 2609.04304 • Published 18 days ago • 69

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Paper • 2609.02750 • Published 19 days ago • 142

upvoted 2 papers 16 days ago

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 18 days ago • 186

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 18 days ago • 98

upvoted 2 papers 17 days ago

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

Paper • 2609.02272 • Published 19 days ago • 7

S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

Paper • 2608.31100 • Published 21 days ago • 40