multi-environment agent evaluation with standardized task interface
Evaluates LLM agents across 8 heterogeneous task environments (OS, DB, KG, DCG, LTP, HH, WS, WB) through a unified Task interface that abstracts environment-specific implementations. Each task environment implements standard methods for sample retrieval, execution, and metric calculation, enabling systematic comparison of agent performance across fundamentally different domains without requiring agents to understand environment-specific APIs.
Unique: First benchmark framework specifically designed for LLM agents with 8 diverse task environments spanning web, database, OS, and game domains. Uses a unified Task interface abstraction that allows heterogeneous environments (WebShop, Mind2Web, ALFWorld, custom games) to expose consistent sample/execute/metric APIs, enabling apples-to-apples agent comparison across fundamentally different interaction paradigms.
vs alternatives: Broader environmental coverage than single-domain benchmarks (e.g., WebShop-only or OS-only) and more realistic than synthetic task collections, providing comprehensive agent capability assessment across real-world scenarios.
session-based agent-task interaction management
Manages bidirectional communication between agents and task environments through a Session abstraction that handles message exchange, conversation history tracking, and state management across multi-turn interactions. The Session interface standardizes how agents send actions and receive observations, enabling any agent implementation (LLM-based, rule-based, or hybrid) to interact with any task environment without environment-specific integration code.
Unique: Implements a unified Session abstraction that decouples agent implementations from environment-specific communication protocols. Agents interact with any task (OS, web, database, game) through identical message-passing semantics, with the Session handling protocol translation and history management transparently.
vs alternatives: Eliminates per-environment adapter code compared to frameworks where agents must implement task-specific interaction logic; enables agent code reuse across all 8 benchmark environments.
web browsing environment with real-world website navigation
Provides a Web Browsing environment (based on Mind2Web) that enables agents to navigate real websites and complete web-based tasks through simulated browser interactions. Agents can search, click links, fill forms, and extract information from web pages. The environment includes rendering of actual web pages and tracking of agent navigation paths. This environment tests agent capabilities in web understanding, navigation planning, and information extraction from complex web interfaces.
Unique: Simulates realistic web browsing with actual website rendering and interaction. Agents navigate real web pages, fill forms, and extract information, testing web understanding and navigation planning on domain-realistic interfaces rather than simplified task environments.
vs alternatives: More realistic than synthetic web environments; tests agent capabilities on actual website navigation and information extraction rather than simplified simulations.
operating system command execution environment with linux shell interaction
Provides an Operating System environment where agents interact with a Linux shell to execute commands, navigate file systems, and complete system administration tasks. Agents generate bash commands that are executed in a sandboxed Linux environment, with output returned as observations. The environment enforces resource limits and safety constraints to prevent harmful operations. This environment tests agent capabilities in command-line reasoning, file system navigation, and system administration.
Unique: Provides a sandboxed Linux shell environment where agents generate and execute bash commands. Agents interact with real file systems, permissions, and shell semantics, testing command-line reasoning and system administration capabilities in a domain-realistic environment with safety constraints.
vs alternatives: More realistic than synthetic OS environments; tests agent capabilities on actual shell commands and file system operations rather than simplified task completion.
database query environment with sql execution and knowledge graph reasoning
Provides Database and Knowledge Graph environments where agents execute SQL queries or SPARQL queries against structured data. The DB environment includes a relational database with schema information; agents must formulate correct SQL queries to retrieve information. The KG environment includes a knowledge graph; agents must reason over relationships and formulate queries. Both environments test agent capabilities in structured data understanding, query formulation, and logical reasoning.
Unique: Provides both relational database (SQL) and knowledge graph (SPARQL) environments where agents must formulate and execute queries. Agents must understand schema/ontology structure and generate syntactically correct queries, testing structured data reasoning and query formulation capabilities.
vs alternatives: Tests agent capabilities on actual database and knowledge graph systems rather than simplified data retrieval; requires agents to understand schema and formulate correct queries.
household task environment with alfworld-based home automation simulation
Provides a Household environment (based on ALFWorld) where agents complete household tasks in a simulated home environment. Tasks include finding objects, manipulating items, and completing household chores. The environment includes a 3D home simulation with object locations, agent actions (move, pick up, put down), and task success criteria. This environment tests agent capabilities in spatial reasoning, object tracking, and sequential task planning in realistic household scenarios.
Unique: Simulates household tasks in a 3D home environment with object locations and agent actions. Agents must reason about spatial relationships, track object locations, and plan sequential actions to complete household tasks, testing spatial reasoning and task planning capabilities.
vs alternatives: More realistic than text-based task environments; tests agent capabilities on spatial reasoning and sequential planning in household scenarios.
lateral thinking puzzle environment with constraint-based problem solving
Provides a Lateral Thinking Puzzles environment where agents solve puzzles that require non-obvious reasoning and constraint satisfaction. Puzzles present a scenario and agents must ask yes/no questions to determine the solution. The environment tracks questions asked, answers provided, and whether agents arrive at correct solutions. This environment tests agent capabilities in hypothesis formation, information seeking, and constraint-based reasoning.
Unique: Provides lateral thinking puzzles that require non-obvious reasoning and hypothesis formation. Agents must ask strategic yes/no questions to determine solutions, testing reasoning capabilities beyond simple task completion or information retrieval.
vs alternatives: Tests creative reasoning and hypothesis formation that simpler task environments cannot measure; requires agents to think beyond obvious solutions.
digital card game environment with strategic gameplay and decision-making
Provides a Digital Card Game environment where agents play strategic card games requiring decision-making, resource management, and opponent modeling. The environment includes game rules, card mechanics, and win conditions. Agents must make strategic decisions about card play, resource allocation, and opponent prediction. This environment tests agent capabilities in strategic reasoning, game-theoretic thinking, and decision-making under uncertainty.
Unique: Provides a strategic card game environment with complex rules, resource management, and decision trees. Agents must reason about game state, predict opponent moves, and make strategic decisions, testing game-theoretic reasoning and strategic planning capabilities.
vs alternatives: More complex than simple game environments; tests agent strategic reasoning and decision-making under uncertainty in games with multiple decision points.
+8 more capabilities