mlsanityData to 7 Oct 2026

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

arXiv 2606.14249 ↗First posted 12 Jun 2026cs.AIcited by 37

Not on the map. Why?

Cited by 29 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. Project homepage: https://darwin-agent.github.io/HarnessX/.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

37 of 55 references.

References · 37

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  8. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  9. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  10. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  11. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  12. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 877
25 more
  1. 2023Large Language Models as Optimizerscited by 830
  2. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  3. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  4. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  5. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  6. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 377
  7. 2024Automated Design of Agentic Systemscited by 360
  8. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  9. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  10. 2024TextGrad: Automatic "Differentiation" via Textcited by 250
  11. 2026Meta-Harness: End-to-End Optimization of Model Harnessescited by 248
  12. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 158
  13. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 119
  14. 2026Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnessescited by 119
  15. 2025A Self-Improving Coding Agentcited by 58
  16. 2024Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agentscited by 50
  17. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 43
  18. 2026Hyperagentscited by 40
  19. 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agentcited by 33
  20. 2026Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agentscited by 22
  21. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 14
  22. 2025A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operatorscited by 14
  23. 2026Memory Intelligence Agentcited by 6
  24. 2026ResMAS: Resilience Optimization in LLM-based Multi-agent Systemscited by 5
  25. 2026K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Controlcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 37.

37 papers.

Sort:

By area:

  1. 2026Recursive Harness Self-Improvementcited by 22
  2. 2026Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectoriescited by 13
  3. 2026Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editablecited by 12
  4. 2026HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolutioncited by 11
  5. 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutioncited by 10
  6. 2026Evo-Bench: Can Language Models Improve Agent Harness?cited by 8
  7. 2026WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolutioncited by 7
  8. 2026HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?cited by 7
  9. 2026HELIX: Model-Harness Co-evolution for Recursive Self-Improvementcited by 6
  10. 2026HarnessOpt-Bench: Evaluating LLMs at Harness Optimizationcited by 5
  11. 2026DarwinX: Evolving Agent Harnesses Through Natural Selectioncited by 5
  12. 2026AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Designcited by 5
25 more
  1. 2026Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnessescited by 4
  2. 2026Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Failscited by 3
  3. 2026RRSI: Regularized Recursive Self-Improvement of Agent Harnessescited by 3
  4. 2026Harness-Zero: Harness Distillation via Agent-as-Harnesscited by 3
  5. 2026Self-Evolving Coding Agentscited by 2
  6. 2026Harness Continual Learning: Continual Adaptation Beyond Model Parameterscited by 2
  7. 2026TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agentscited by 2
  8. 2026Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systemscited by 1
  9. 2026EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agentscited by 1
  10. 2026LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineeringcited by 1
  11. 2026Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimizationcited by 1
  12. 2026What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agentscited by 1
  13. 2026HarnessPAI: An Evolving Harness for Physical AIcited by 1
  14. 2026ADIAS: Automated Design of Interactive Agentic Systemscited by 0
  15. 2026WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editingcited by 0
  16. 2026PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Pluginscited by 0
  17. 2026LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Taskscited by 0
  18. 2026RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agentscited by 0
  19. 2026EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuningcited by 0
  20. 2026SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Timecited by 0
  21. 2026VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understandingcited by 0
  22. 2026Composing Task-specific Agent Harnesses at Test Time with Reusable Primitivescited by 0
  23. 2026Harness Annealing: Learning to Act with Less External Controlcited by 0
  24. 2026CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolutioncited by 0
  25. 2026The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gatecited by 0