M Saad Salman

MSS444's activity

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

upvoted 3 papers 1 day ago

Omega-S: A Functional Resilience Index for LLM Fine-Tuning

Paper • 2608.03887 • Published 9 days ago • 6

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Paper • 2608.10299 • Published 3 days ago • 122

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Paper • 2608.11079 • Published 2 days ago • 12

upvoted 3 papers 2 days ago

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Paper • 2608.04205 • Published 9 days ago • 34

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published 7 days ago • 51

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Paper • 2608.08311 • Published 5 days ago • 79

upvoted a paper 3 days ago

Characterizing the Quality Profile of AI-Generated C++ in Production

Paper • 2608.06640 • Published 7 days ago • 10

upvoted 11 papers 6 days ago

What AI Red-Team Evaluations Can and Cannot Prove

Paper • 2607.21735 • Published 21 days ago • 5

Self-Evolving Coding Agents

Paper • 2608.03392 • Published 9 days ago • 8

Lossless Tensor Compression as Program Synthesis

Paper • 2608.02162 • Published 10 days ago • 15

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Paper • 2608.00782 • Published 12 days ago • 16

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

Paper • 2608.03764 • Published 9 days ago • 27

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Paper • 2608.05139 • Published 8 days ago • 27

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 9 days ago • 35

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

Paper • 2608.05000 • Published 7 days ago • 59

ChronoVision: Temporal Reasoning via Latent State Reconstruction

Paper • 2608.05631 • Published 7 days ago • 39

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 7 days ago • 34

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

Paper • 2608.06060 • Published 7 days ago • 40

upvoted 2 papers 8 days ago

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Paper • 2608.00155 • Published 13 days ago • 25

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

Paper • 2608.02499 • Published 10 days ago • 24