task: acp_nexta_gen dataset_name: acp_nexta_gen include: _gen_yaml_2shot fewshot_config: sampler: first_n samples: - context: "A robot is in a grid and can only move to places that are connected to its current position. The grid size is 5x5, and the locations are of the form fi-jf (e.g., f3-2f or f0-1f). The grid cells are connected to their neighbors (e.g., f1-2f is connected to the four neighbors f0-2f, f2-2f, f1-1f, and f1-3f). Some positions on the grid are locked and can be opened with a key of a matching shape. The robot has an arm that can pick up a key when the key is in same location as the robot and the arm is empty. There are 2 keys in 1 different shapes: Key key0-1 is of shape shape0, Key key0-0 is of shape shape0. Currently, the robot is at position f4-0f and its arm is empty. All the positions are open except the following: f4-2f has shape0 shaped lock. Key key0-0 is at position f3-0f. Key key0-1 is at position f1-3f. The goal is to reach a state where the following facts hold: Key key0-0 is at f2-0f location and Key key0-1 is at f1-3f location. The available actions are: (unlock ?curpos ?lockpos ?key ?shape) - unlock place ?lockpos with key ?key of shape ?shape from current position place ?curpos, (move ?curpos ?nextpos) - travel from the current position ?curpos to the next position ?nextpos, (pickup ?curpos ?key) - pick up key ?key from place ?curpos, (pickup-and-loose ?curpos ?newkey ?oldkey) - pick up the key ?newkey at the current position place ?curpos and loose the key ?oldkey being held, and (putdown ?curpos ?key) - put down the key ?key at the current position ?curpos." question: "What is the next action that takes us towards the goal?" answer: "(move f4-0f f3-0f)" - context: "There are several cities, each containing several locations, some of which are airports. There are also trucks, which can drive within a single city, and airplanes, which can fly between airports. The goal is to get some packages from various locations to various new locations. There are 2 trucks and 1 airplane, as well as 4 packages. There are 4 locations across 2 cities. The locations are in cities as follows: l0-1 and l0-0 are in c0; l1-1 and l1-0 are in c1. Currently, t0 is at l0-1, a0 is at l0-0, t1 and p1 are at l1-0, p2, p0, and p3 are in t1. The goal is to reach a state where the following facts hold: p3 is at l0-1, p2 is at l1-0, p1 is at l1-0, and p0 is at l0-0. The available actions are: (load-truck ?obj ?truck ?loc) - load object ?obj into truck ?truck at location ?loc, (load-airplane ?obj ?airplane ?loc) - load the object ?obj from location ?loc onto the airplane ?airplane, (unload-truck ?obj ?truck ?loc) - unload the object ?obj from the truck ?truck at location ?loc, (unload-airplane ?obj ?airplane ?loc) - unload object ?obj from airplane ?airplane at location ?loc, (drive-truck ?truck ?loc-from ?loc-to ?city) - drive the truck ?truck in city ?city from location ?loc-from to location ?loc-to, and (fly-airplane ?airplane ?loc-from ?loc-to) - operate the airplane ?airplane from airport ?loc-from to airport ?loc-to." question: "What is the next action that takes us towards the goal?" answer: "(drive-truck t0 l0-1 l0-0 c0)" doc_to_text: "**Question**: {{context}} {{question}} Each action starts with an opening parenthesis and ends with closing parenthesis. Provide only the action. **Final Answer**:" filter_list: - name: "acp_grammar_parse" filter: - function: "ACP_grammar_filter" grammar_task: "action_name" - function: "take_first"