# US 2026/0278333 A1 · Artificial intelligence device for prompt-driven neuro-symbolic agent and method thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0278333 A1
- Document ID: US20260278333A1
- Status: Published application
- Kind: A1
- Application number: 19/566,585
- Filed: 2026-03-13
- Published: 2026-09-17
- Earliest claimed: 2025-03-14
- Assignees: LG Electronics Inc.
- Applicants: LG Electronics Inc.
- Inventors: Manasa BHARADWAJ
- Web page: https://patentgrep.com/patent/US20260278333A1

## CPC

- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06F 16/2471: {Distributed queries}
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/092: Reinforcement learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/025: Extracting rules from data
- G06N 5/046: Forward inferencing; Production systems
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for controlling an artificial intelligence (AI) device can include receiving a user query indicating a target task and an observation from a target environment, obtaining a set of domain constraints, a set of contextual priors, and state information based on the user query and the observation, constructing an aggregated prompt sequence that fuses the user query and the observation with the set of domain constraints, the set of contextual priors, and the state information, generating, by a large language model, an action based on the aggregated prompt sequence, and outputting the action for execution within the target environment. Also, the set of domain constraints and the set of contextual priors can restrict an available action space of the large language model to prevent execution of impossible or contextually invalid operations.

## Claims

### Claim 1

A method for controlling an artificial intelligence (AI) device, the method comprising:
receiving, by a processor in the AI device, a user query indicating a target task and an observation from a target environment;
obtaining, by the processor, a set of domain constraints, a set of contextual priors and state information based on the user query and the observation;
constructing an aggregated prompt sequence that fuses the user query and the observation with the set of domain constraints, the set of contextual priors, and the state information;
generating, by a large language model, an action based on the aggregated prompt sequence; and
outputting the action for execution within the target environment,
wherein the set of domain constraints and the set of contextual priors restrict an available action space of the large language model to prevent execution of impossible or contextually invalid operations.

### Claim 2 (depends on 1)

The method of claim 1, wherein the obtaining the set of domain constraints, the set of contextual priors, and the state information includes:
parsing, by a manager module executed by the processor, the user query and the observation to extract an operational domain and at least one target entity; and
querying a plurality of independent symbolic modules based on the operational domain and the at least one target entity.

### Claim 3 (depends on 1)

The method of claim 1, wherein the set of domain constraints is retrieved from an environment constitution module and defines rules, unalterable physical laws or boundaries of the target environment, and
wherein the set of domain constraints prunes physically impossible actions from the available action space of the large language model.

### Claim 4 (depends on 1)

The method of claim 1, wherein the set of contextual priors is retrieved from a commonsense augmentation module including at least one of a lookup table, a database or a relational knowledge graph, and
wherein the set of contextual priors maps target objects to at least one of statistically probable locations, functional affordances, or relational prerequisites within the target environment to prevent contextually absurd actions or contextually absurd strategies.

### Claim 5 (depends on 1)

The method of claim 1, wherein the state information is maintained by a progress tracking module configured as a finite state machine or programming logic, and
wherein the state information includes a sequential log of one or more of prior executed actions, current sub-goals, and intermediate thought checkpoints.

### Claim 6 (depends on 1)

The method of claim 1, wherein the constructing the aggregated prompt sequence further includes:
injecting a predefined list of permissible action templates and a plurality of few-shot examples configured to teach the large language model a structured reasoning format.

### Claim 7 (depends on 6)

The method of claim 6, wherein the structured reasoning format mandates that the large language model alternates between generating an intermediate thought validating a sub-goal and outputting the action based on a strict syntax defined by one of the permissible action templates.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
receiving an updated observation from the target environment in response to the execution of the action;
updating the state information based on the updated observation;
obtaining an updated set of domain constraints, an updated set of contextual priors, and updated state information;
constructing an updated aggregated prompt sequence based on the updated set of domain constraints, the updated set of contextual priors, and the updated state information; and
generating a subsequent action based on the updated aggregated prompt sequence.

### Claim 9 (depends on 1)

The method of claim 1, wherein the obtaining and the constructing are orchestrated by a meta large language model configured to dynamically evaluate the user query, autonomously retrieve the set of domain constraints and the set of contextual priors, and compile the aggregated prompt sequence before passing the aggregated prompt sequence to the large language model for inference.

### Claim 10 (depends on 1)

The method of claim 1, wherein the target environment is a real world physical environment and the action is output as a motor control signal to a robotic apparatus, or
wherein the target environment is a digital environment and the action is output as an automated web browser interaction.

### Claim 11 (depends on 1)

The method of claim 1, wherein the state information includes an execution step count or a repeated action counter, and
wherein the method further comprises:
monitoring the execution step count or the repeated action counter during execution of the target task;
comparing the execution step count or the repeated action counter with a predetermined threshold number; and
in response to determining that the execution step count or the repeated action counter exceeds the predetermined threshold number, modifying the aggregated prompt sequence to inject a corrective heuristic,
wherein the corrective heuristic forces the large language model to select an alternative action pathway to prevent the artificial intelligence device from entering an endless execution loop.

### Claim 12 (depends on 1)

The method of claim 1, wherein the observation from the target environment includes visual data,
wherein the receiving the observation further includes:
processing the visual data through a vision-language model or an image encoder to extract a textual state description of the target environment, and
wherein the textual state description identifies objects and spatial geometries within the target environment and is fused into the aggregated prompt sequence to ground the large language model in a current physical reality of the target environment.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
in response to the target environment returning an error observation indicating that the action failed to execute successfully, updating the state information to flag the action as a failed operation for a current environmental state, and constructing a subsequent aggregated prompt sequence that includes the failed operation and instructs the large language model to bypass the failed operation during a subsequent inference cycle.

### Claim 14

An artificial intelligence (AI) device, comprising:
a memory configured to store information for a large language model; and
a controller configured to:
receive a user query indicating a target task and an observation from a target environment,
obtain a set of domain constraints, a set of contextual priors and state information based on the user query and the observation,
construct an aggregated prompt sequence that fuses the user query and the observation with the set of domain constraints, the set of contextual priors, and the state information,
generate, by the large language model, an action based on the aggregated prompt sequence, and
output the action for execution within the target environment,
wherein the set of domain constraints and the set of contextual priors restrict an available action space of the large language model to prevent execution of impossible or contextually invalid operations.

### Claim 15 (depends on 14)

The AI device of claim 14, wherein the controller is further configured to:
retrieve the set of domain constraints from an environment constitution module, the set of domain constraints defining rules, unalterable physical laws or boundaries of the target environment, and
wherein the set of domain constraints prunes the available action space of the large language model.

### Claim 16 (depends on 14)

The AI device of claim 14, wherein the controller is further configured to:
retrieve the set of contextual priors from a commonsense augmentation module including at least one of a lookup table, a database or a relational knowledge graph, and
wherein the set of contextual priors maps target objects to at least one of statistically probable locations, functional affordances, or relational prerequisites within the target environment to prevent contextually absurd actions or strategies.

### Claim 17 (depends on 14)

The AI device of claim 14, wherein the state information is maintained by a progress tracking module configured as a finite state machine or programming logic, and
wherein the state information includes a sequential log of one or more of prior executed actions, current sub-goals, and intermediate thought checkpoints.

### Claim 18 (depends on 14)

The AI device of claim 14, wherein the controller is further configured to:
inject a predefined list of permissible action templates and a plurality of few-shot examples configured to teach the large language model a structured reasoning format to construct the aggregated prompt sequence, and
wherein the structured reasoning format mandates that the large language model alternates between generating an intermediate thought validating a sub-goal and outputting the action based on a strict syntax defined by one of the permissible action templates.

### Claim 19 (depends on 14)

The AI device of claim 14, wherein the state information includes an execution step count or a repeated action counter,
wherein the controller is further configured to:
monitor the execution step count or the repeated action counter during execution of the target task,
compare the execution step count or the repeated action counter with a predetermined threshold number, and
in response to determining that the execution step count or the repeated action counter exceeds the predetermined threshold number, modify the aggregated prompt sequence to inject a corrective heuristic, and
wherein the corrective heuristic forces the large language model to select an alternative action pathway to prevent the artificial intelligence device from entering an endless execution loop.

### Claim 20

A non-transitory computer readable medium storing computer-executable instructions that when executed by a processor, cause the processor to perform the operations of:
receiving a user query indicating a target task and an observation from a target environment;
obtaining a set of domain constraints, a set of contextual priors, and state information based on the user query and the observation;
constructing an aggregated prompt sequence that fuses the user query and the observation with the set of domain constraints, the set of contextual priors, and the state information;
generating, by a large language model, an action based on the aggregated prompt sequence; and
outputting the action for execution within the target environment,
wherein the set of domain constraints and the set of contextual priors restrict an available action space of the large language model to prevent execution of impossible or contextually invalid operations.
