GitSwarm: Decentralized Compounding Inference
cs.AI, cs.LG
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/karpathy/nanochat
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
- ResearchGym: Evaluating Language Model Agents on Real-World AI Research
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Effective Strategies for Asynchronous Software Engineering Agents
- Accelerating scientific discovery with Co-Scientist
- AIRA_2: Overcoming Bottlenecks in AI Research Agents
- Learning the ARTS of Search for Automated Discovery
- Scaling Test-Time Compute for Agentic Coding
- Meta-Harness: End-to-End Optimization of Model Harnesses
- AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
- Rethinking Thinking Tokens: LLMs as Improvement Operators
- Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
- Residual Matrix Transformers: Scaling the Size of the Residual Stream
- MLGym: A New Framework and Benchmark for Advancing AI Research Agents
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- MemGPT: Towards LLMs as Operating Systems
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems