The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
The paper introduces agent-native primitives, reusable units that pair a resource with a resident LLM that applies it in context, and HEELO, a harness-engineering framework that composes task-specific graphs of these primitives, verifies…
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face
- Discovery linkHugging Face
- Linked in sourceView arXiv page
- Linked in sourceView PDF
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
The paper introduces agent-native primitives, reusable units that pair a resource with a resident LLM that applies it in context, and HEELO, a harness-engineering framework that composes task-specific graphs of these primitives, verifies results against environment evidence, and revises failing primitives. The authors report gains across more than twenty benchmarks and on 46 real-world tasks on their heelo.dev platform, where connecting Claude Code and Codex to HEELO raised completed tasks from 9 to 39 and 35 respectively. These results are the authors' own reported numbers.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; results come from the authors' own benchmarks and heelo.dev platform, and the paper's model names and benchmark versions should be verified.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; results come from the authors' own benchmarks and heelo.dev platform, and the paper's model names and benchmark versions should be verified.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
Agent-native primitives pair each resource with a resident LLM that applies it in context and communicates with other primitives.
Source: Hugging Face ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseHEELO composes primitives into task-specific graphs, verifies outcomes against environment evidence, and revises implicated primitives.
Source: Hugging Face ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseOn 46 real-world tasks, completed tasks rose from 9 to 39 for Claude Code and from 9 to 35 for Codex when connected to HEELO.
Source: Hugging Face ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseReported gains include Terminal-Bench 4.0 resolution rising from 37.3% to 55.5% under Codex with Dev-Primitives.
Source: Hugging Face ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; results come from the authors' own benchmarks and heelo.dev platform, and the paper's model names and benchmark versions should be verified.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
If the gains hold under independent evaluation, reusable, self-applying resource primitives could reduce the per-harness engineering needed to make agents complete real-world tasks end to end.
Limits and open questions
Source claims not independently checked; results come from the authors' own benchmarks and heelo.dev platform, and the paper's model names and benchmark versions should be verified.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →