Divide, Diagnose, and Compose: Optimizing Agentic Pipelines and Harnesses
cs.MA
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- PostTrainBench: Can LLM Agents Automate LLM Post-Training?
- Gemma 4 Technical Report
- Qwen3.5-Omni Technical Report
- MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
- TextGrad: Automatic "Differentiation" via Text
- Multi-agent Architecture Search via Agentic Supernet
- Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
- BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
- Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Related papers
- MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
- Iterative Negotiation and Oversight: A Case Study in Decentralized Air Traffic Management
- Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts
- A-MapReduce: Executing Wide Search via Agentic MapReduce
- AgentCue: Statistical Summaries for Guiding Decentralized Multi-Agent Self-Organization
- Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning