Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 675
Sofia Castillo
nicholasbrown20
AI & ML interests
Paper replication and lightweight experiments.
Recent Activity
upvoted a paper about 3 hours ago
Raven: The Harness of Harnesses for Composable Agentic Intelligence upvoted a paper about 3 hours ago
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search upvoted a paper about 3 hours ago
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy DistillationOrganizations
None yet
upvoted 6
papers about 3 hours ago
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 323
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Paper • 2609.35347 • Published • 182
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 291
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 443
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Paper • 2610.22276 • Published • 91
upvoted 10
papers about 5 hours ago
Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
Paper • 2610.19696 • Published • 18
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Paper • 2608.30821 • Published • 118
DAPD: Dual-Anchored Policy Distillation
Paper • 2608.01735 • Published • 159
Learning from the Self-future: On-policy Self-distillation for dLLMs
Paper • 2606.18195 • Published • 175
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Paper • 2609.06107 • Published • 210
OmniEdu: Open Foundation Models for Learning and Teaching
Paper • 2609.23088 • Published • 239
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 271
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Paper • 2609.29233 • Published • 274
Aspire: Can Models Self-Evolve from Vague Goals?
Paper • 2608.31111 • Published • 413
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 517
upvoted a paper 4 days ago