M Saad Salman

MSS444's activity

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

upvoted 9 papers 1 day ago

Memory for Large Language Models

Paper • 2607.25380 • Published 4 days ago • 7

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published 3 days ago • 25

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

Paper • 2607.25675 • Published 4 days ago • 60

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

Paper • 2607.27652 • Published 2 days ago • 3

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

Paper • 2607.27919 • Published 2 days ago • 48

Can Large Language Models Execute Parent Orders?

Paper • 2607.28410 • Published 2 days ago • 14

MemHarness: Memory Is Reconstructed, Not Replayed

Paper • 2607.28272 • Published 2 days ago • 13

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published 2 days ago • 40

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 3 days ago • 247

upvoted a paper 3 days ago

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

Paper • 2607.25091 • Published 5 days ago • 6

upvoted a paper 4 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 5 days ago • 419

upvoted 3 papers 5 days ago

OpenForgeRL: Train Harness-native Agents in Any Environment

Paper • 2607.21557 • Published 9 days ago • 8

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published 10 days ago • 24

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 8 days ago • 47

upvoted 4 papers 8 days ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 14 days ago • 137

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

Paper • 2607.19604 • Published 11 days ago • 17

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Paper • 2607.20145 • Published 10 days ago • 72

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 9 days ago • 149

upvoted 2 papers 11 days ago

RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

Paper • 2607.11683 • Published 19 days ago • 148

RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources

Paper • 2606.29538 • Published 16 days ago • 142