Split (1)

train · 9.18k rows

messages listlengths 3 127	domain stringclasses 7 values	dataset stringclasses 11 values
[ { "role": "system", "content": "Role: Operate as a language world model for a mobile accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	android	AndroidControl
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a web search and page-browsing environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action bloc...	search	OpenResearcher
[ { "role": "system", "content": "Role: Serve as a language world model for a web search and page-browsing environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation,...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a language world model for a mobile accessibility-control environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Ob...	android	AndroidControl
[ { "role": "system", "content": "Role: Operate as a language world model for a web search and page-browsing environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a software-engineering shell testbed. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, the provided `###[Task Description]`, curr...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a state-transition world model for a terminal command-execution environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turns ...	terminal	TMax
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of an MCP business-tool environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action block, and pri...	mcp	AWM
[ { "role": "system", "content": "Role: Operate as a language world model for a terminal command-execution environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and e...	terminal	TMax
[ { "role": "system", "content": "Role: Function as the environment model for a mobile accessibility-control environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and h...	android	AndroidControl
[ { "role": "system", "content": "Role: Serve as a language world model for a desktop accessibility-control environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation...	os	A11y-CUA
[ { "role": "system", "content": "Role: You are a state-transition world model for a desktop accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier tur...	os	A11y-CUA
[ { "role": "system", "content": "Role: Act as a language world model for an MCP business-tool environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observation]`, the c...	mcp	AWM
[ { "role": "system", "content": "Role: Act as a language world model for a web search and page-browsing environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a language world model for a software-engineering shell testbed. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the provided `###[Task D...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a web search and page-browsing environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a deterministic language world model for a software-engineering shell testbed. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, and pre...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a deterministic language world model for a software-engineering shell testbed. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, and pre...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a state-transition world model for a terminal command-execution environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turns ...	terminal	TMax
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a software-engineering shell testbed. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action block, and...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a language world model for a software-engineering shell testbed. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the provided `###[Task D...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a state-transition world model for a browser accessibility environment with reference IDs. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and ...	web	web__weblinx_browsergym
[ { "role": "system", "content": "Role: You are a state-transition world model for a mobile accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turn...	android	AndroidControl
[ { "role": "system", "content": "Role: Act as a language world model for a terminal command-execution environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observation]...	terminal	TMax
[ { "role": "system", "content": "Role: Operate as a language world model for an MCP business-tool environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and earlier t...	mcp	AWM
[ { "role": "system", "content": "Role: Act as a language world model for a terminal command-execution environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observation]...	terminal	TMax
[ { "role": "system", "content": "Role: Operate as a language world model for a desktop accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, an...	os	A11y-CUA
[ { "role": "system", "content": "Role: Operate as a language world model for a mobile accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a state-transition world model for an MCP business-tool environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turns as the c...	mcp	AWM
[ { "role": "system", "content": "Role: Function as the environment model for a browser accessibility-control environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and ...	web	A3-Synth
[ { "role": "system", "content": "Role: You are a deterministic language world model for an MCP business-tool environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, and previou...	mcp	AWM
[ { "role": "system", "content": "Role: You are a deterministic language world model for a web search and page-browsing environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, a...	search	OpenResearcher
[ { "role": "system", "content": "Role: Serve as a language world model for a desktop accessibility-control environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation...	os	A11y-CUA
[ { "role": "system", "content": "Role: Serve as a language world model for a software-engineering shell testbed. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation, issue...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a language world model for a terminal command-execution environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Obse...	terminal	TMax
[ { "role": "system", "content": "Role: You are a state-transition world model for a web search and page-browsing environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turn...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a software-engineering shell testbed. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, the provided `###[Task Description]`, action t...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a terminal command-execution environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `##...	terminal	TMax
[ { "role": "system", "content": "Role: You are a deterministic language world model for a terminal command-execution environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, and...	terminal	TMax
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a web search and page-browsing environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action bloc...	search	OpenResearcher
[ { "role": "system", "content": "Role: Function as the environment model for a metadata-only MCP analytics and notebook environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, a...	mcp	mcp__fleet_tool_use_difficult_envs
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a web search and page-browsing environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a software-engineering shell testbed. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action block, and...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a state-transition world model for a web search and page-browsing environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turn...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a language world model for a mobile accessibility-control environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Ob...	android	AndroidControl
[ { "role": "system", "content": "Role: Act as a language world model for a web search and page-browsing environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	search	OpenResearcher
[ { "role": "system", "content": "Role: Operate as a language world model for a mobile accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	android	AndroidControl
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a terminal command-execution environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action block,...	terminal	TMax
[ { "role": "system", "content": "Role: You are a deterministic language world model for a browser accessibility environment with reference IDs. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, curre...	web	web__weblinx_browsergym
[ { "role": "system", "content": "Role: Operate as a language world model for a mobile accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	android	AndroidControl
[ { "role": "system", "content": "Role: Function as the environment model for a software-engineering shell testbed. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and history...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a language world model for a metadata-only MCP analytics and notebook environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the la...	mcp	mcp__fleet_tool_use_difficult_envs
[ { "role": "system", "content": "Role: You are a state-transition world model for a mobile accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turn...	android	AndroidControl
[ { "role": "system", "content": "Role: Act as a language world model for a web search and page-browsing environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	search	OpenResearcher
[ { "role": "system", "content": "Role: Function as the environment model for a mobile accessibility-control environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and h...	android	AndroidControl
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a mobile accessibility-control environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a deterministic language world model for a browser accessibility-control environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current action, ...	web	A3-Synth
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of an MCP business-tool environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action block, and pri...	mcp	AWM
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a mobile accessibility-control environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, action bloc...	android	AndroidControl
[ { "role": "system", "content": "Role: Serve as a language world model for a software-engineering shell testbed. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation, issue...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a deterministic language world model for a software-engineering editor and shell environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current ...	swe	swe__openhands_sft
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a software-engineering shell testbed. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, the provided `###[Task Description]`, curr...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a language world model for an MCP business-tool environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Observation]...	mcp	AWM
[ { "role": "system", "content": "Role: Serve as a language world model for a web search and page-browsing environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation,...	search	OpenResearcher
[ { "role": "system", "content": "Role: Operate as a language world model for a browser accessibility-control environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, an...	web	A3-Synth
[ { "role": "system", "content": "Role: You are a language world model for a mobile accessibility-control environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Ob...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a state-transition world model for a desktop accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier tur...	os	A11y-CUA
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a web search and page-browsing environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	search	OpenResearcher
[ { "role": "system", "content": "Role: Act as a language world model for a mobile accessibility-control environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a web search and page-browsing environment. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, latest `###[Observation]`, action text, ...	search	OpenResearcher
[ { "role": "system", "content": "Role: Operate as a language world model for a software-engineering shell testbed. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and earli...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a deterministic language world model for a software-engineering editor and shell environment. Predict the environment observation caused by the already-issued action, and nothing else.\n\nInput: Use all provided goal or task context, recent observation, current ...	swe	swe__openhands_sft
[ { "role": "system", "content": "Role: You are a language world model for a mobile accessibility-control environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Ob...	android	AndroidControl
[ { "role": "system", "content": "Role: Operate as a language world model for a web search and page-browsing environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a browser accessibility-control environment. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, latest `###[Observation]`, action text,...	web	A3-Synth
[ { "role": "system", "content": "Role: You are a state-transition world model for a desktop accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier tur...	os	A11y-CUA
[ { "role": "system", "content": "Role: Serve as a language world model for a browser accessibility-control environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation...	web	A3-Synth
[ { "role": "system", "content": "Role: Operate as a language world model for a web search and page-browsing environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and...	search	OpenResearcher
[ { "role": "system", "content": "Role: Act as a language world model for a web search and page-browsing environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	search	OpenResearcher
[ { "role": "system", "content": "Role: You are a language world model for a terminal command-execution environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[Obse...	terminal	TMax
[ { "role": "system", "content": "Role: Act as a language world model for an MCP business-tool environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observation]`, the c...	mcp	AWM
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a web search and page-browsing environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	search	OpenResearcher
[ { "role": "system", "content": "Role: Operate as a language world model for a terminal command-execution environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and e...	terminal	TMax
[ { "role": "system", "content": "Role: Function as the environment model for a software-engineering shell testbed. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and history...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are an observation generator for a language world model of a software-engineering editor and shell environment. The action has already occurred; simulate the environment result rather than agent intent.\n\nInput: Use the goal or task context, current observation, ac...	swe	swe__openhands_sft
[ { "role": "system", "content": "Role: You are the simulator side of a language world model for a web search and page-browsing environment. The agent has already selected an action, and your job is to predict the environment response.\n\nInput: Treat the goal or metadata, latest `###[Observation]`, current `...	search	OpenResearcher
[ { "role": "system", "content": "Role: Act as a language world model for a mobile accessibility-control environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	android	AndroidControl
[ { "role": "system", "content": "Role: Act as a language world model for a mobile accessibility-control environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observatio...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a terminal command-execution environment. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, latest `###[Observation]`, action text, an...	terminal	TMax
[ { "role": "system", "content": "Role: Serve as a language world model for an MCP business-tool environment. Your output should be the environment state immediately after the recorded action, not the agent behavior before or after it.\n\nInput: Combine the goal or task context, current observation, issued ac...	mcp	AWM
[ { "role": "system", "content": "Role: You are a state-transition world model for a mobile accessibility-control environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turn...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a language world model for a browser accessibility-control environment. Your responsibility is to simulate the environment after an action has already been issued, not to act as the agent.\n\nInput: This prompt accepts the goal or task context, the latest `###[O...	web	A3-Synth
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a software-engineering shell testbed. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, the provided `###[Task Description]`, action t...	swe	SWE-Gym
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a software-engineering shell testbed. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, the provided `###[Task Description]`, action t...	swe	SWE-Gym
[ { "role": "system", "content": "Role: Operate as a language world model for an MCP business-tool environment. You model how the environment changes after an issued action and report only the resulting observation.\n\nInput: Interpret the goal or task metadata, latest observation, action block, and earlier t...	mcp	AWM
[ { "role": "system", "content": "Role: You are a post-action environment simulator for a web search and page-browsing environment. The input action is already fixed; your role is to predict what the environment exposes next.\n\nInput: Use the available goal, metadata, latest `###[Observation]`, action text, ...	search	OpenResearcher
[ { "role": "system", "content": "Role: Act as a language world model for a desktop accessibility-control environment. You predict the post-action observation of the environment; you are not the acting agent, planner, or tool executor.\n\nInput: Use the goal or task description, the most recent `###[Observati...	os	A11y-CUA
[ { "role": "system", "content": "Role: Function as the environment model for a mobile accessibility-control environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and h...	android	AndroidControl
[ { "role": "system", "content": "Role: You are a state-transition world model for an MCP business-tool environment. Your prediction is the next observation after the given action, not a recommendation or solution.\n\nInput: Treat the goal, metadata, latest observation, action text, and earlier turns as the c...	mcp	AWM
[ { "role": "system", "content": "Role: Function as the environment model for a web search and page-browsing environment. Given the action already chosen by another agent, infer the next visible observation without taking agency yourself.\n\nInput: Read the goal or metadata, current observation, action, and h...	search	OpenResearcher

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.