Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Hugging Face Daily Papers Papers
terminal-agents test-time-scaling action-verification agentic-ai agent-harness trajectory-optimization

Summary

Mid-Harness introduces a method for terminal agents that samples and verifies candidate actions at the model-harness boundary before execution, boosting TerminalBench-Lite Pass@1 from 50.00% to 68.03% with a GPT-5.6 Solverifier and showing action scaling is an efficient test-time compute target alongside trajectory scaling.

Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor command (e.g., wrong package install) can change the environment in ways that hinder subsequent progress, even when the model could generate a better alternative. We investigate whether allocating test-time compute at the model-harness boundary can improve action reliability and trajectory success, and what makes this allocation effective. To study these questions, we introduce Mid-Harness, which samples and verifies candidate actions before forwarding one for execution, while keeping the generator and harness unchanged. With a TMAX-9B generator, more action sampling yields little benefit under weak verification, whereas a capable verifier can exploit useful alternatives from the same generator. On TerminalBench-Lite, a GPT-5.6 Sol verifier raises Pass@1 from 50.00% for the base agent to 68.03% with 8 sampled actions. When the same TMAX-9B model serves as the verifier, pairwise verification performs best among the evaluated verification mechanisms. Distilling responses from the stronger verifier into TMAX-9B further improves Pass@1, while leaving the action generator unchanged. With TMAX-9B on TerminalBench-Lite, combining action and trajectory scaling reaches higher success at lower estimated token cost than generating more trajectories alone. Mid-Harness also improves performance across additional models, benchmarks, and harnesses. These findings identify action scaling as a promising target for test-time compute scaling in terminal agents.
Original Article
View Cached Full Text

Cached at: 10/01/26, 08:23 AM

Paper page - Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Source: https://huggingface.co/papers/2609.39982 Authors:

,

,

,

,

,

,

,

,

,

Abstract

Terminalagentsactthroughstochasticmodelgenerations,yettheabilitytogenerateausefulactiondoesnotensureitsreliableexecution.Apoorcommand(e.g.,wrongpackageinstall)canchangetheenvironmentinwaysthathindersubsequentprogress,evenwhenthemodelcouldgenerateabetteralternative.Weinvestigatewhetherallocatingtest-timecomputeatthemodel-harnessboundarycanimproveactionreliabilityandtrajectorysuccess,andwhatmakesthisallocationeffective.Tostudythesequestions,weintroduceMid-Harness,whichsamplesandverifiescandidateactionsbeforeforwardingoneforexecution,whilekeepingthegeneratorandharnessunchanged.WithaTMAX-9Bgenerator,moreactionsamplingyieldslittlebenefitunderweakverification,whereasacapableverifiercanexploitusefulalternativesfromthesamegenerator.OnTerminalBench-Lite,[email protected]%forthebaseagentto68.03%with8sampledactions.WhenthesameTMAX-9Bmodelservesastheverifier,pairwiseverificationperformsbestamongtheevaluatedverificationmechanisms.DistillingresponsesfromthestrongerverifierintoTMAX-9BfurtherimprovesPass@1,whileleavingtheactiongeneratorunchanged.WithTMAX-9BonTerminalBench-Lite,combiningactionandtrajectoryscalingreacheshighersuccessatlowerestimatedtokencostthangeneratingmoretrajectoriesalone.Mid-Harnessalsoimprovesperformanceacrossadditionalmodels,benchmarks,andharnesses.Thesefindingsidentifyactionscalingasapromisingtargetfortest-timecomputescalinginterminalagents.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.39982

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.39982 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.39982 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.39982 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Self-Harness: Harnesses That Improve Themselves

Hacker News Top

Self-Harness introduces a new paradigm where LLM-based agents iteratively improve their own operating harness by mining model-specific weaknesses, proposing harness modifications, and validating them through regression testing, achieving substantial performance gains on Terminal-Bench-2.0 across multiple base models.

Harness Self-Evolution for Long-Horizon Terminal Agents

arXiv cs.AI

The paper presents RiseHarness, a framework from Tencent and multiple universities that iteratively improves agent harnesses for long-horizon terminal tasks while keeping model weights fixed, analyzing successful and failed runs to progressively integrate better execution mechanisms.

Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction

Hugging Face Daily Papers

The paper introduces SHIFT, a framework that builds multi-agent harnesses per-query using a learned local LLM architect and value function combined with Monte Carlo tree search, achieving ~80% mean accuracy across 9,193 tasks and outperforming 17 baselines while reducing execution token costs by 32% in its cheaper mode.