Agora: Git as Shared Memory for Collective AutoResearch
Paper • 2609.18094 • Published • 57
🔄 In a Training Loop
Pratyay Banerjee
Neilblaze
AI & ML interests
IR, NLP, Pattern Recognition, xAI, Interpretability, Evals
Recent Activity
upvoted a paper 1 day ago
Agora: Git as Shared Memory for Collective AutoResearch upvoted a paper 1 day ago
Normalized Low-Rank AdaptationOrganizations
upvoted 20
papers 1 day ago
Normalized Low-Rank Adaptation
Paper • 2608.31036 • Published • 57
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2609.20784 • Published • 56
Self-Evolving Search Index
Paper • 2609.19656 • Published • 60
Verifiable Social Reasoning for LLM Assistants
Paper • 2609.17496 • Published • 65
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Paper • 2609.17708 • Published • 71
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Paper • 2609.13285 • Published • 81
Language Models Can Control Their Own Attention
Paper • 2609.02737 • Published • 79
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 79
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
Paper • 2609.08572 • Published • 107
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Paper • 2609.15364 • Published • 84
An Empirical Study of Harness Design for Coding Agents
Paper • 2609.20804 • Published • 85
Omni Interaction Agent Technical Report
Paper • 2609.08977 • Published • 96
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Paper • 2609.05571 • Published • 114
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Paper • 2609.04172 • Published • 101
LatentPress: Context Compression Beyond Text and Vision
Paper • 2609.01507 • Published • 120
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 130
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Paper • 2609.15779 • Published • 151
Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems
Paper • 2609.02750 • Published • 144
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Paper • 2609.19969 • Published • 178