Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/openclaw/openclaw
Terminology
Sources
- General Agent Evaluation
- Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
- Large Language Models as Tool Makers
- Why Do Multi-Agent LLM Systems Fail?
- FireAct: Toward Language Agent Fine-tuning
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
- Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
- WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models
- AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
- From Question Answering to Task Completion: A Survey on Agent System and Harness Design
- FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
- Distilling the Knowledge in a Neural Network
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Understanding the planning of LLM agents: A survey
- OpenVLA: An Open-Source Vision-Language-Action Model
- Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
- Similarity of Neural Network Representations Revisited
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