pith. sign in

arxiv: 2603.25723 · v2 · pith:FN2I4DW2new · submitted 2026-03-26 · 💻 cs.CL · cs.AI

Natural-Language Agent Harnesses

classification 💻 cs.CL cs.AI
keywords agentharnessharnessesnatural-languagearoundcodedocumentsnlahs
0
0 comments X p. Extension
pith:FN2I4DW2 Add to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{FN2I4DW2}

Prints a linked pith:FN2I4DW2 badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to inspect, compare, transfer, and ablate. This paper asks whether the reusable design pattern of an agent harness can be represented as an executable natural-language object. We introduce Natural-Language Agent Harnesses (NLAHs), editable documents that describe run-level harness policy, and Intelligent Harness Runtime (IHR), a shared runtime that interprets these documents into agent calls, handoffs, state updates, validation gates, and artifact contracts. Across coding, terminal-use, and computer-use benchmarks, IHR-executed NLAHs achieve comparable task outcomes to code and prompted realizations, while exposing much shorter static harness policies. Module ablations further show that explicit harness modules are analyzable. These results suggest that agent harnesses can be turned from incidental glue around models into scientific representation objects.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

    cs.AI 2026-05 unverdicted novelty 8.0

    Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.

  2. Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

    cs.AI 2026-05 unverdicted novelty 7.0

    Memory for long-horizon agents should preserve distinctions that affect decisions under a fixed budget, not descriptive features, yielding an exact forgetting boundary and a new online learner DeMem with regret guarantees.

  3. Agentic MIP Research: Accelerated Constraint Handler Generation

    cs.AI 2026-05 unverdicted novelty 7.0

    LLM agents in a solver-aware harness recover global constraints from MIP formulations, generate executable propagation-only handlers for SCIP, and solve five additional MIPLIB 2017 instances.

  4. Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning

    cs.CL 2026-05 unverdicted novelty 7.0

    OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.

  5. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

    cs.AI 2026-04 unverdicted novelty 7.0

    Proposes a levels x laws taxonomy for world models in AI agents, defining L1-L3 capabilities across physical, digital, social, and scientific regimes while reviewing over 400 works to outline a roadmap for advanced ag...

  6. AI4BayesCode: From Natural Language Descriptions to Validated Modular Stateful Bayesian Samplers

    stat.CO 2026-05 unverdicted novelty 6.0

    AI4BayesCode generates validated modular stateful MCMC samplers from natural language Bayesian model descriptions via LLM translation, modular blocks, and recursive stateful composition.

  7. AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs

    cs.CL 2026-04 unverdicted novelty 6.0

    AutoPyVerifier learns compact sets of executable Python verifiers from labeled LLM outputs via LLM synthesis and DAG search, improving objective prediction by up to 55 F1 points and downstream LLM accuracy by up to 17 points.

  8. Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

    cs.AI 2026-04 unverdicted novelty 6.0

    Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.

  9. Code as Agent Harness

    cs.CL 2026-05 accept novelty 5.0

    A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed ...

  10. Harness Engineering as Categorical Architecture

    cs.PL 2026-05 unverdicted novelty 5.0

    Categorical Architecture triple (G, Know, Phi) supplies the formal theory for composing LLM agent harnesses with structurally preserved certificates.

  11. Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems

    cs.AI 2026-05 unverdicted novelty 5.0

    A systems-level data model for preserving typed, addressable, versioned, and dependency-aware intermediate artifacts in agentic AI systems to improve long-term inspectability and maintainability.

  12. Nautilus: From One Prompt to Plug-and-Play Robot Learning

    cs.RO 2026-05 unverdicted novelty 5.0

    NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.

  13. From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work

    cs.AI 2026-05 conditional novelty 5.0

    Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.