Proposer-Agent-Evaluator
Basic Information
Website: https://yanqval.github.io/PAE/
Short description: A system for vision foundation models to propose and practice skills in new environments [source]
Intended uses: What does the developer state that the system is intended for?: Complete general web-based tasks
Date(s) deployed: December 17, 2024 [source]
Developer
Website: https://yanqval.github.io/PAE/
Legal name: University of California Berkeley (et al.) [source]
Entity type: Academic Institutions, Industry Organization
Country (location of developer or first author's first affiliation): California, USA [source]
Safety policies: What safety and/or responsibility policies are in place?: None
System Components
Backend model(s): What model(s) are used to power the system?: LLaVa-34B and -7B [source]
Public model specification: Is there formal documentation on the system’s intend...: None
Description of reasoning, planning, and memory implementation: How does the syst...: PAE uses chain-of-thought reasoning before taking actions [source].
Observation space: What is the system able to observe while 'thinking'?: PAE's observation space consists of a screenshot of the current web page with the different interactive elements identified [source].
Action space/tools: What direct actions can the system take?: "The action space contains primitive web operations such as clicking on links and typing into text boxes" [source].
User interface: How do users interact with the system?: The primary way to interact with PAE is with their open-sourced code and API [source].
Development cost and compute: What is known about the development costs?: 30k trajectories * 1/512 hour/trajectory = ~60 hours of AWS P4 instance (8xA100 40G) per task, see Figure 6 [source]
Guardrails & Oversight
Accessibility of components
Weights: Are model parameters available?: Available [source]
Data: Is data available?: Available [source]
Code: Is code available?: Available [source]
Documentation: Is documentation available?: Available [source]
Scaffolding: Is system scaffolding available?: Available [source]
Controls and guardrails: What notable methods are used to protect against harmfu...: PAE allows a maximum of 10 steps. Additionally, it has a system prompts which steers the system away from harmful/unhelpful behaviors [source].
Monitoring and shutdown procedures: Are there any notable methods or protocols t...: N/A Open-source
Customer and usage restrictions: Are there know-your-customer measures or other ...: None
Evaluation
Notable benchmark evaluations (e.g., on SWE-Bench Verified): WebVoyager (33%), WebArena Easy (25.7%) [source]
Bespoke testing (e.g., demos): They test generalization on 85 real-world websites not included in other benchmarks. They test the automated evaluator with human baselines [source].
Safety: Have safety evaluations been conducted by the developers? What were the ...: None
Publicly reported external red-teaming or comparable auditing
Personnel: Who were the red-teamers/auditors?: None
Scope, scale, access, and methods: What access did red-teamers/auditors have and...: None
Findings: What did the red-teamers/auditors conclude?: None
Ecosystem
Interoperability with other systems: What tools or integrations are available?: Any web interface
Usage statistics and patterns: Are there any notable observations about usage?: Github repo has 42 stars and 2 forks [source].
Other notes (if any): --