This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2605.07630 · AGENTS · SUBMITTED 11 MAY · 20:36 UTC · FRESHNESS STALE
ARXIV:2605.07630AGENTSSUBMITTED 11 MAY · 20:36 UTCFRESHNESS STALEZhengyang Tang · Yi Zhang · Chenxin Li · Xin Lai · Pengyuan Lyu · Yiduo Guo · +15 at arXiv
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.
Opportunity summary
Pain A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.
Evidence 0 refs | 4 sources | 83% coverage
Blocker Evidence unverified
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements. Existing evaluations often cannot tell.
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell.
ScienceToStartup currently rates this 7.0/10 on the public viability pass. When a phone-use agent avoids harm, does that show safety, or simply inability to act? A public repository is linked, so build verification can…
Agents moved forward this cycle; last verified May 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.
Continue into Read for claims, analysis, references, and neighboring papers.
Opportunity summary
Score7.0Public score shown from the verified overall while the stale axis breakdown refreshesAnalysis summary
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.
Loading BUILD…
WATCHTOWER
No verified watchtower monitor rows yet.
FORESIGHT
No prediction yet — minted on next Foresight batch.
OPPORTUNITYKERNEL CHANGES SINCE LAST VIEW
No verified OpportunityKernel changes since the last view.
COMPETITIVE LANDSCAPE UPDATES
No verified competitive landscape changes yet.
RELATED PAPER UPDATES
No verified related paper changes yet.
SIGNAL CANVAS HISTORY AND DELTAS
No Signal Canvas history deltas yet.
TIMELINE
Save this paper to start tracking momentum - commits, demos, and score changes appear here.
No tracked events yet.
Score trend will appear after multiple data points.
BUZZ
Buzz trend pending.
Paper Pack
10.48550/arXiv.2605.07630A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.
Abstract
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Parse run linkedA document parse run is attached to this paper.
Proof status
unverified0 refs; 4 sources; 83% coverage.
What was readable
Derived fallback: Estimated from adjacent evidence; not verified from source.
Viability
Time to MVP
Commercial
Export
Preparing verified analysis
Dimensions overall score 7.0
RESULT
ScienceToStartup currently rates this 7.0/10 on the public viability pass. When a phone-use agent avoids harm, does that show safety, or simply inability to act? A public repository is linked, so build verification can inspect implementation evidence instead of treating the pape...
PROBLEM
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements. Existing evaluations often cannot tell.
METHOD
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell.
WHY NOW
Agents moved forward this cycle; last verified May 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.
Abstract-backed public claims while anchored extraction refreshes.
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements. Existing evaluations often cannot tell.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
ScienceToStartup currently rates this 7.0/10 on the public viability pass. When a phone-use agent avoids harm, does that show safety, or simply inability to act? A public repository is linked, so build verification can inspect implementation evidence instead of treating the paper as PDF-only.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
Agents moved forward this cycle; last verified May 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
Preview the source document here, or use the hero PDF action for a new tab.
Reference metadata is not materialized in the public index yet. The source PDF remains the authority; cache refresh is optional.
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Foundation
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.
Concepts
Methods
Materials
Markets
Competitors
A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.
Segment
Agents
Adoption evidence
Public code linked for build inspection
Commercial read
7.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2605.07630 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.
Hacker News
Not indexed yet
Not indexed yet
Bluesky
Not indexed yet
Commercially relevant
/api/v1/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents/paper-pack/api/v1/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents/build-passport/api/openapi.json/api/mcpsciencetostartup://surfaces/paper-workspacepaper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state{
"contract_version": "paper-r2",
"paper_id": "97dde4d0-a83c-4973-bbae-99c3fe42450b",
"arxiv_id": "2605.07630",
"canonical_route": "/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"active_tab": "synced from current hash by the drawer client",
"selected_artifact": "safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"endpoints": {
"paper_pack": "/api/v1/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents/paper-pack",
"build_passport": "/api/v1/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents/build-passport",
"mcp_resource": "sciencetostartup://surfaces/paper-workspace"
}
}Canonical route, proof status, last verified, refs, sources, and coverage.
Page Freshness
Canonical route: /paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents
This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.
Endpoint list, payload shape, route context, and copyable handoff data.
Agent Handoff
Canonical ID safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents | Route /paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agentsMCP example
{
"tool": "get_paper",
"arguments": {
"arxiv_id": "2605.07630"
}
}source_context
{
"surface": "paper",
"mode": "paper",
"query": "Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents",
"normalized_query": "2605.07630",
"route": "/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"paper_ref": "safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"topic_slug": null,
"benchmark_ref": null,
"dataset_ref": null
}Verdict, compute envelope, blockers, signature state, and receipt links.
Paper proof page receipt window
/buildability/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents
Subject: Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
Verdict
Build Now
Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.
Time to first demo
Insufficient data
No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.
Structured compute envelope
Insufficient data
Visual citations from the paper document graph.
Visual citation anchors from the paper document graph.
This equation captures one of the core mathematical components of the system. Safe-action rate = Nsafe N , Unsafe-action rate = Nunsafe N , No-useful-action rate = Nno-useful N .
Page and bbox are available; crop image is pending.
This equation captures one of the core mathematical components of the system. Safe-action rate + Unsafe-action rate + CFR = 1, 1−CFR = Nsafe + Nunsafe N .
Page and bbox are available; crop image is pending.
This equation captures one of the core mathematical components of the system. General Phone-Use SR (%) Safe-Action Rate (%) (c) General SR vs. 1−CFR (ρ=0.922). (d) Strict vs. minimal (∆CFR=0.0).
Page and bbox are available; crop image is pending.
The application/ld+json payload rendered for agents.
{
"@context": "https://schema.org",
"@graph": [
{
"@type": "WebPage",
"@id": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents#webpage",
"url": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"name": "Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents",
"description": "A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.",
"isPartOf": {
"@id": "https://sciencetostartup.com/#website"
}
},
{
"@type": "ScholarlyArticle",
"@id": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents#scholarlyArticle",
"headline": "Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents",
"description": "A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.",
"url": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents",
"sameAs": "https://arxiv.org/abs/2605.07630",
"identifier": {
"@type": "PropertyValue",
"propertyID": "arXiv",
"value": "2605.07630"
},
"isAccessibleForFree": true,
"isPartOf": {
"@id": "https://sciencetostartup.com/#website"
},
"datePublished": "2026-05-08T11:58:57.000Z",
"author": [
{
"@type": "Person",
"name": "Zhengyang Tang"
},
{
"@type": "Person",
"name": "Yi Zhang"
},
{
"@type": "Person",
"name": "Chenxin Li"
},
{
"@type": "Person",
"name": "Xin Lai"
},
{
"@type": "Person",
"name": "Pengyuan Lyu"
},
{
"@type": "Person",
"name": "Yiduo Guo"
},
{
"@type": "Person",
"name": "Weinong Wang"
},
{
"@type": "Person",
"name": "Junyi Li"
},
{
"@type": "Person",
"name": "Yang Ding"
},
{
"@type": "Person",
"name": "Huawen Shen"
},
{
"@type": "Person",
"name": "Zhengyao Fang"
},
{
"@type": "Person",
"name": "Xingran Zhou"
},
{
"@type": "Person",
"name": "Liang Wu"
},
{
"@type": "Person",
"name": "Fei Tang"
},
{
"@type": "Person",
"name": "Sunqi Fan"
},
{
"@type": "Person",
"name": "Shangpin Peng"
},
{
"@type": "Person",
"name": "Zheng Ruan"
},
{
"@type": "Person",
"name": "Anran Zhang"
},
{
"@type": "Person",
"name": "Benyou Wang"
},
{
"@type": "Person",
"name": "Chengquan Zhang"
},
{
"@type": "Person",
"name": "Han Hu"
}
],
"codeRepository": "https://github.com/tangzhy/PhoneSafety",
"additionalProperty": [
{
"@type": "PropertyValue",
"propertyID": "viabilityScore",
"value": 7
},
{
"@type": "PropertyValue",
"propertyID": "researchDomain",
"value": "Agents"
},
{
"@type": "PropertyValue",
"propertyID": "commercialReadiness",
"value": "code, repo url"
}
]
},
{
"@type": "SoftwareSourceCode",
"@id": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents#software",
"name": "Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents - Source Code",
"description": "A new benchmark and evaluation framework to distinguish true safety in phone-use agents from mere inability to act, enabling targeted improvements.",
"codeRepository": "https://github.com/tangzhy/PhoneSafety",
"url": "https://github.com/tangzhy/PhoneSafety"
},
{
"@type": "BreadcrumbList",
"itemListElement": [
{
"@type": "ListItem",
"position": 1,
"name": "Home",
"item": "https://sciencetostartup.com"
},
{
"@type": "ListItem",
"position": 2,
"name": "Agents",
"item": "https://sciencetostartup.com/topics"
},
{
"@type": "ListItem",
"position": 3,
"name": "Safe, or Simply Incapable? Rethinking Safety Evaluation for ",
"item": "https://sciencetostartup.com/paper/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents"
}
]
}
]
}No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.
Receipt path
/buildability/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents
Paper ref
safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents
arXiv id
2605.07630
Generated at
2026-05-11T20:36:04.167Z
Evidence freshness
stale
Last verification
2026-05-11T20:36:04.167Z
Sources
4
References
0
Coverage
83%
Lineage hash
676e15e0641535eb2b49d447211e92ff4f5f33008d6a8e5df4a5b7fba9536abb
Canonical opportunity-kernel lineage hash.
External signature
unsigned_external
No founder, registry, pilot, or production-adoption signature is attached to this receipt.
Verification
not_verified
Verification is blocked until an external signature is provided.
Pending verification refs / 4 sources / Verification pending
references
2/3 checks · 67%
Build Passport
Build passport pending - Proof Lab budget No verified cost estimate / $7.00 cap
status
missing
reason
passport_row_missing
proof status
unverified
cost/budget
No verified cost estimate
confidence low
next verification path
Build brief missing until Build Passport data exists.
Source missing: Build Passport payload.
Experiment plan missing until prototype path is available.
No prototype path attached.
Validation checklist missing until required assets, cost, and regulatory flags are verified.
No checklist artifact is attached to the Build Passport payload.
Derived signals show verified:false until source-backed receipts exist.
Evidence coverage
OpportunityKernel evidence_receipt
0 refs / 4 sources / 83% coverage
stale
Verify missing sources before using this as buyer proof. verified:false
Build readiness
BuildPassport EvidenceState
passport absent
stale
Run Proof Lab or inspect typed missing state. verified:false
Artifact maturity
GitHub and Hugging Face maturity payloads
No public artifact surface observed
stale
Open source artifacts or mark the gap as missing. verified:false
Technical feasibility
partial
Current read
Runnable path is not fully verified.
Evidence
No Build Passport payload attached.
Gaps
Next test
Run minimal reproduction from the Build Passport prototype path.
Market urgency
missing
Current read
Buyer urgency is not verified from source.
No named scientific founder assigned.
Paper authors are not treated as operators without consent.
People
No named person assigned.
Gaps
Next verification path
Prototype owner missing.
Build Passport does not name an implementer.
People
No named person assigned.
ARTIFACTS
No public artifacts yet.
DEFENSIBILITY
Defensibility and confidence evidence pending.
Evidence
0 references, 4 sources, 83% evidence coverage.
Gaps
Next test
Collect buyer interview, deployment evidence, or cited demand signal.
Buyer clarity
missing
Current read
No budget owner is verified for this paper.
Evidence
Build tab has no CRM, procurement, or operator source.
Gaps
Next test
Map target operator, economic buyer, and procurement trigger.
Defensibility
missing
Current read
Defensibility signals are missing.
Evidence
No defensibility receipt attached.
Gaps
Next test
Refresh defensibility bars with source receipts.
Integration burden
missing
Current read
No public implementation surface observed.
Evidence
No GitHub or Hugging Face payload attached.
Gaps
Next test
Write integration checklist from prototype path and target workflow.
Capital intensity
missing
Current read
No observed cost estimate is verified.
Evidence
Cost passport has no observed_usd value.
Gaps
Next test
Run cost passport or mark the cost field not applicable.
Regulatory load
missing
Current read
No regulatory classification is attached.
Evidence
Build Passport ledger does not include regulatory flags.
Gaps
Next test
Classify regulatory flags before commercialization planning.
Gaps
Next verification path
Operator workflow not sourced.
No buyer or workflow interview attached.
People
No named person assigned.
Gaps
Next verification path
No GTM owner verified.
No CRM or outreach source attached.
People
No named person assigned.
Gaps
Next verification path
Regulatory need unclassified.
No clinical or regulatory source attached.
People
No named person assigned.
Gaps
Next verification path