DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Paper • 2607.16617 • Published • 134
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
Organizations
None yet
upvoted 4
papers 1 day ago
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Paper • 2607.19604 • Published • 14
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Paper • 2607.20145 • Published • 56
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Paper • 2607.21461 • Published • 124
upvoted 3
papers 5 days ago
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
Paper • 2607.11683 • Published • 143
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Paper • 2606.29538 • Published • 139
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Paper • 2607.18110 • Published • 14
upvoted 4
papers 6 days ago
Rethinking the Evaluation of Harness Evolution for Agents
Paper • 2607.12227 • Published • 9
Loop the Loopies!
Paper • 2607.16051 • Published • 71
Recursive Harness Self-Improvement
Paper • 2607.15524 • Published • 24
From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality
Paper • 2607.13196 • Published • 29
upvoted 4
papers 9 days ago
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
Paper • 2607.11849 • Published • 33
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Paper • 2607.12463 • Published • 108
Self-Improvements in Modern Agentic Systems: A Survey
Paper • 2607.13104 • Published • 31
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 100
upvoted a paper 10 days ago
upvoted 4
papers 12 days ago
Unified Audio Intelligence Without Regressing on Text Intelligence
Paper • 2607.05196 • Published • 23
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
Paper • 2607.06065 • Published • 8
Gemma 4 Technical Report
Paper • 2607.02770 • Published • 72
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Paper • 2607.03451 • Published • 33