GCRI · Kecerdasan Buatan dan Sistem Otonom
Sistem agentik
Agentic AI sistem pursue goals by planning and taking actions: calling tools, browsing, writing and running code, or operating other software, sometimes over long tasks with little supervision. Autonomy brings usefulness and new failure modes, from compounding errors to misuse of granted permissions. This page sets out how agents fail, how their actions can be bounded and overseen, and what evidence serves those who build, deploy and govern them.
Agentic systems on the record.
Agentic systems: how the risk develops.
Tool access, delegated authority and safe execution. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.
Errors compound over steps
Each step in a long task can go wrong, and an early mistake shapes later actions. Small per-step error rates add up over many steps.
Permissions define the blast radius
An agent can only do harm with the access it has been given. Broad credentials, write access and payment rights turn errors or manipulation into real-world consequences.
Untrusted inputs steer behaviour
Agents read web pages, documents and messages that may contain instructions. Prompt injection can redirect an agent to act against its user.
Oversight must be designed in
Humans cannot review every action of a fast agent. Approval steps for consequential actions, logging and the ability to stop and roll back are design choices.
Agent oversight console.
Layar yang akan digunakan sebuah tim untuk mengikuti subjek ini: ukuran, status, dan keputusannya. Nama adalah contoh dan nilai bersifat ilustratif.
Agent oversight console
Agentic systems · Agent sandbox · Session AG-6627
Tool calls
- 10:34Infosearch(documents) · read-only
- 10:51Inforun_model(flood_nowcast) · sandbox
- 10:51Gerbangsend_message(external) · needs approval
- 10:53Errorwrite_file(outside workspace) · denied
Kebijakan
- Lingkup
- workspace only
- External actions
- human approval
- Spend limit
- 43 units
- Kill switch
- Armed
Actions by approval class
Agents that act need guardrails in every domain they touch.
- EnergiKeterkaitanAutomated control of grids needs strict human oversight.What to watchOverride and rollback design
- KesehatanKeterkaitanAgents handling health data raise privacy and safety risks.What to watchAccess scopes and logs
- AirKeterkaitanAutomation of utility operations must fail safe.What to watchFail-safe behaviour
Agentic system studies are designed for the seri Teknologi Eksponensial. The OWASP Top 10 for LLM applications lists failure modes such as excessive agency and prompt injection; the page describes them without exploit detail.
- Incident reports involving agents.
- Designs for oversight and permission scoping.
How agentic systems is modelled, measured and tested.
Model, asumsi, data, dan ketidakpastiannya, dalam bentuk yang akan diperiksa ilmuwan atau insinyur. Strukturnya mengikuti metode yang dipublikasikan. Nilai yang digambar bersifat ilustratif, bukan temuan.
Model sistem
The couplings between the systems in agentic systems: signs of influence, a reinforcing and a balancing loop, and cross-links where stress jumps.
Apa yang diukur, dan seberapa baik.
Setiap indikator membawa satuan, frekuensi, jenis sumber di baliknya, dan label bukti yang akan dibawa suatu nilai. Tidak ada nilai yang ditampilkan: sebuah program menyediakannya berdasarkan wewenangnya sendiri.
| Indikator | Unit | Kadensi | Jenis sumber | Label |
|---|---|---|---|---|
| Task success rate on agent benchmarks | percent of tasks completed correctly | per evaluation | Agent benchmark results | DILAPORKAN |
| Actions requiring human approval | percent of consequential actions | per deployment | Deployment configuration | DINYATAKAN |
| Prompt injection success rate | percent of attempts succeeding | per evaluation | Security testing | TERAMATI |
| Agent incidents | count by severity | setiap bulan | Incident reports | DILAPORKAN |
| Actions logged and attributable | percent of agent actions | per deployment | Audit logs | TERAMATI |
| Mean task length before human intervention | steps or minutes | per evaluation | Evaluation logs | TERAMATI |
Asal bukti.
Set data publik bernama dan catatan kelembagaan, masing-masing dengan kelas lisensinya. Sumber berdasarkan perjanjian hanya digunakan sesuai ketentuannya dan tidak pernah diterbitkan ulang.
| Sumber | Apa yang diberikannya | Kelas lisensi |
|---|---|---|
| OWASP Top 10 for LLM Applications and agentic security guidance | Risks such as prompt injection and excessive agency | Open, CC BY-SA 4.0 |
| Published agent benchmarks such as SWE-bench and related suites | Task-based evaluation of agents | Open, licence per benchmark (to check) |
| Kerangka Manajemen Risiko AI NIST (NIST AI Risk Management Framework) | Practices for governing and measuring AI risk | Public domain, US government |
| AI Incident Database | Reported incidents involving AI sistem | Open, licence to check |
| Developer system cards describing agent safeguards | Developer-reported agent evaluations and controls | Public documents, terms per developer |
Siapa yang memutuskan, dan apa yang dilayani bukti.
Studio Kecerdasan Buatan dan Sistem prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.
| Siapa yang memutuskan | Pertanyaannya | Bukti yang dilayani halaman ini |
|---|---|---|
| Deploying organisations | Which actions an agent may take alone and which need approval | Permission patterns; evaluation results |
| Security teams | How to protect agents from manipulation | Injection testing; incident evidence |
| Regulator | What oversight to require for autonomous AI actions | Oversight design evidence |
Keluaran yang dihasilkan topik ini
- Permission and approval design patterns for agents
- Agent evaluation protocols covering long tasks
- Prompt injection test suites for deployments
- Logging and rollback requirements
What designers and evaluators ask.
- What actions can the agent take, with whose authority, and which are reversible?
- How does it behave when instructions are ambiguous, conflicting or malicious?
- Can a human see what it is doing, understand why and stop it in time?
- How do errors compound over long sequences of steps?
How agents fail.
An agent combines a model’s reasoning with permissions in the world. Small errors in early steps can compound across a long task. Agents can misinterpret goals, pursue them in unintended ways or take shortcuts that satisfy a metric but not the intent. Content the agent reads, such as a web page or document, can contain instructions designed to hijack it, an attack known as prompt injection.
The more permissions an agent holds, the larger the potential harm. Sistem that coordinate several agents add further failure modes, as agents pass errors to each other or interact in unforeseen ways.
Designing for safe execution.
- 01
Least privilege
Granting only the permissions a task needs, with sandboxes and spending or action limits, drawing on keamanan siber dan kriptografi.
- 02
Human oversight points
Requiring confirmation for consequential or irreversible actions. Too many prompts lead to rubber-stamping, so placement matters.
- 03
Task-based evaluation
Testing agents on realistic multi-step tasks in controlled environments, using Evaluasi AI dan rekayasa penjaminan. Simulated environments miss some real-world complexity.
- 04
Logging and audit
Recording actions and reasoning traces so incidents can be reconstructed. Traces may not fully reflect how a model reached a decision.
Cara hal ini dikaji, dan apa yang tidak dapat dinyatakan metodenya.
- 01Evaluasi AI dan rekayasa penjaminanKasus penjaminan untuk sistem AI · Red teaming terstruktur · Pemantauan pascapenerapanDiterapkan di sini
- 02Keamanan siber dan kriptografiPemodelan ancaman aplikasi AI · Integritas rantai pasok model · Pengujian pertahanan terhadap injeksiDiterapkan di sini
- 03Kecerdasan buatan dan pembelajaran mesinAnalisis pergeseran distribusi · Fine-tuning untuk penggunaan tertentu · Metode interpretabilitasDiterapkan di sini
- 04Probabilitas dan statistikaKetidakpastian pada skor tolok ukur · Penilaian kalibrasi · Sampel auditDiterapkan di sini
Where this page’s references lead.
Badan dan dokumen yang menjadi acuan halaman ini. Status dan edisi berubah; setiap tautan menuju badan penerbitnya.
Tanya jawab.
What is an AI agent?
What is prompt injection?
How can agent risk be reduced?
Should agents ever act without human approval?
Can agents be evaluated before deployment?
Does the platform build agents?
Kontribusikan bukti dari halaman ini.
Laporan is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.
- SurelGerbang GW-GCRIKirim dari halaman iniBukti, koreksi, kasus, metode, tinjauan, terjemahan, atau masukan profil. Kiriman tiba dengan label halaman ini, sehingga editor pemiliknya menerimanya.
- ZenodoDeposit terbukaDeposit dan ajukan ke komunitasTerbitkan catatan Anda sendiri di Zenodo dengan ORCID iD Anda, lalu ajukan ke komunitas Reports di sana. Kurator meninjaunya; DOI tetap milik Anda.
- LaporanGCRILihat semua cara berkontribusiJenis kontribusi, cara masing-masing ditinjau, kredit yang Anda terima, lisensinya, dan apa yang tidak pernah diterima.
Jangan pernah mengirim data pribadi, rincian infrastruktur sensitif, atau apa pun yang tidak berhak Anda bagikan. Kontribusi ditinjau sebelum digunakan. Mengirimkannya tidak memberikan hak kepenulisan atau editorial, dan sponsor tidak pernah membeli sebuah temuan.
Bawa metode, dataset, atau pertanyaan.
Informasi dan pertanyaan sudah terbuka hari ini. Sebuah pertanyaan menerima nomor referensi dan menyebutkan langkah berikutnya; lamaran, pembayaran, alokasi komputasi, dan pendaftaran hanya dibuka ketika tim, ketentuan, dan kapasitas tinjauannya tersedia.
Dokumen hukum.
Peta, data, dan gambar di situs ini ditampilkan untuk konteks dan informasi umum. Semua itu bukan nasihat, prakiraan, atau peringatan; batasan informasinya dijelaskan dalam Penafian dan Pemberitahuan Data.