project/paperbench/paperbench/agents/aisi-basic-agent/_basic_agent_iterative.py [67:127]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *, init: Solver | list[Solver] | None = None, tools: list[Tool] | Solver | None = None, cache: bool | CachePolicy = False, max_attempts: int = 1, message_limit: int | None = None, token_limit: int | None = None, real_time_limit: int | None = None, max_tool_output: int | None = None, score_value: ValueToFloat | None = None, incorrect_message: str | Callable[[TaskState, list[Score]], str] = DEFAULT_INCORRECT_MESSAGE, continue_message: str = DEFAULT_CONTINUE_MESSAGE, submit_name: str = DEFAULT_SUBMIT_NAME, submit_description: str = DEFAULT_SUBMIT_DESCRIPTION, disallow_submit: bool = False, **kwargs: Unpack[BasicAgentDeprecatedArgs], ) -> Solver: """Basic ReAct agent. Agent that runs a tool use loop. Tailor the model's instructions by passing a `system_message()` and/or other steps to `init` (if no `init` is specified then a default system message will be used). Use `max_attempts` to support additional submissions if the initial submission(s) are incorrect. Submissions are evaluated using the task's main scorer, with value of 1.0 indicating a correct answer. Scorer values are converted to float (e.g. "C" becomes 1.0) using the standard value_to_float() function. Provide an alternate conversion scheme as required via `score_value`. Args: init: (Solver | list[Solver] | None): Agent initialisation (defaults to system_message with basic ReAct prompt) tools (list[Tool | ToolDef] | Solver | None): Tools available for the agent. Either a list of tools or a Solver that can yield dynamic tools per-sample. cache: (bool | CachePolicy): Caching behaviour for generate responses (defaults to no caching). max_attempts (int): Maximum number of submissions to accept before terminating. message_limit (int | None): Limit on messages in sample before terminating agent. If not specified, will use limit_messages defined for the task. If there is none defined for the task, 50 will be used as a default. token_limit (int | None): Limit on tokens used in sample before terminating agent. max_tool_output (int | None): Maximum output length (in bytes). Defaults to max_tool_output from active GenerateConfig. score_value (ValueToFloat): Function used to extract float from scores (defaults to standard value_to_float()) incorrect_message (str | Callable[[TaskState, list[Score]], str]): User message reply for an incorrect submission from the model. Alternatively, a function which returns a message. continue_message (str): User message to urge the model to continue when it doesn't make a tool call. **kwargs (Any): Deprecated arguments for backward compatibility. Returns: Plan for agent. """ # resolve deprecated for arg, value in kwargs.items(): if arg == "max_messages": # deprecated, don't warn yet message_limit = int(cast(int, value)) # resolve init if init is None: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - project/paperbench/paperbench/agents/aisi-basic-agent/_basic_agent_plus.py [74:134]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - *, init: Solver | list[Solver] | None = None, tools: list[Tool] | Solver | None = None, cache: bool | CachePolicy = False, max_attempts: int = 1, message_limit: int | None = None, token_limit: int | None = None, real_time_limit: int | None = None, max_tool_output: int | None = None, score_value: ValueToFloat | None = None, incorrect_message: str | Callable[[TaskState, list[Score]], str] = DEFAULT_INCORRECT_MESSAGE, continue_message: str = DEFAULT_CONTINUE_MESSAGE, submit_name: str = DEFAULT_SUBMIT_NAME, submit_description: str = DEFAULT_SUBMIT_DESCRIPTION, disallow_submit: bool = False, **kwargs: Unpack[BasicAgentDeprecatedArgs], ) -> Solver: """Basic ReAct agent. Agent that runs a tool use loop. Tailor the model's instructions by passing a `system_message()` and/or other steps to `init` (if no `init` is specified then a default system message will be used). Use `max_attempts` to support additional submissions if the initial submission(s) are incorrect. Submissions are evaluated using the task's main scorer, with value of 1.0 indicating a correct answer. Scorer values are converted to float (e.g. "C" becomes 1.0) using the standard value_to_float() function. Provide an alternate conversion scheme as required via `score_value`. Args: init: (Solver | list[Solver] | None): Agent initialisation (defaults to system_message with basic ReAct prompt) tools (list[Tool | ToolDef] | Solver | None): Tools available for the agent. Either a list of tools or a Solver that can yield dynamic tools per-sample. cache: (bool | CachePolicy): Caching behaviour for generate responses (defaults to no caching). max_attempts (int): Maximum number of submissions to accept before terminating. message_limit (int | None): Limit on messages in sample before terminating agent. If not specified, will use limit_messages defined for the task. If there is none defined for the task, 50 will be used as a default. token_limit (int | None): Limit on tokens used in sample before terminating agent. max_tool_output (int | None): Maximum output length (in bytes). Defaults to max_tool_output from active GenerateConfig. score_value (ValueToFloat): Function used to extract float from scores (defaults to standard value_to_float()) incorrect_message (str | Callable[[TaskState, list[Score]], str]): User message reply for an incorrect submission from the model. Alternatively, a function which returns a message. continue_message (str): User message to urge the model to continue when it doesn't make a tool call. **kwargs (Any): Deprecated arguments for backward compatibility. Returns: Plan for agent. """ # resolve deprecated for arg, value in kwargs.items(): if arg == "max_messages": # deprecated, don't warn yet message_limit = int(cast(int, value)) # resolve init if init is None: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -