M Saad Salman

MSS444's activity

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

upvoted 9 papers 1 day ago

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

Paper • 2608.00155 • Published 7 days ago • 12

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

Paper • 2608.02499 • Published 4 days ago • 23

DiffusionGemma Technical Report

Paper • 2608.00146 • Published 7 days ago • 33

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

Paper • 2608.01755 • Published 4 days ago • 139

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 4 days ago • 57

ExplainBench: Evaluating Code Explanations from Agents

Paper • 2607.26451 • Published 9 days ago • 12

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 3 days ago • 20

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

Paper • 2608.04003 • Published 3 days ago • 28

PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning

Paper • 2608.01837 • Published 4 days ago • 37

upvoted a paper 3 days ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published 4 days ago • 29

upvoted 3 papers 4 days ago

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Paper • 2607.29677 • Published 7 days ago • 20

AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

Paper • 2607.28617 • Published 8 days ago • 36

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 12 days ago • 99

upvoted 7 papers 7 days ago

Memory for Large Language Models

Paper • 2607.25380 • Published 10 days ago • 13

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published 9 days ago • 28

DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space

Paper • 2607.25675 • Published 10 days ago • 65

Harness-G: A Graph-Structured Harness for Search Agents

Paper • 2607.27652 • Published 8 days ago • 5

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

Paper • 2607.27919 • Published 8 days ago • 58

Can Large Language Models Execute Parent Orders?

Paper • 2607.28410 • Published 8 days ago • 17

MemHarness: Memory Is Reconstructed, Not Replayed

Paper • 2607.28272 • Published 8 days ago • 15