ADIAS: Automated Design of Interactive Agentic Systems

arXiv:2608.06410 · cs.AI, cs.CL, cs.MA · Submitted 2026-08-03 · Read on arXiv

Lekang Jiang, Bohan Tang, Stephan Goetz, Yiwen Guo

cs.AI, cs.CL, cs.MA

Submitted: 2026-08-03

Updated: 2026-08-10

Comments: 23 pages, 7 tables, 5 figures

Code: https://github.com/scylj1/adias

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Harness — 43× in this paper · explained in 2 episodes
• Benchmark — 40× in this paper · explained in 2 episodes
• Agentic System — 9× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Agent Harness — 6× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Failure Modes — 4× in this paper · explained in 3 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Agent Architecture — 3× in this paper · explained in 1 episode
• Agentic Harness Engineering — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Embodied AI — 2× in this paper · explained in 2 episodes
• Evaluation Protocol — 2× in this paper · explained in 2 episodes
• Failure Attribution — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Evolutionary Search — 1× in this paper · explained in 2 episodes
• Feedback Loop — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Planner — 1× in this paper · explained in 3 episodes

Sources

• MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
• SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
• Understanding the planning of LLM agents: A survey
• MemoHarness: Agent Harnesses That Learn from Experience
• Meta-Harness: End-to-End Optimization of Model Harnesses
• AutoFlow: Automated Workflow Generation for Large Language Model Agents
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• Position: Agentic Evolution is the Path to Evolving LLMs
• AutoHarness: improving LLM agents by automatically synthesizing a code harness
• GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
• TTHE: Test-Time Harness Evolution
• Code as Agent Harness
• Archon: An Architecture Search Framework for Inference-Time Techniques
• Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
• Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
• Rethinking the Evaluation of Harness Evolution for Agents
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
• From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

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