# US 2026/0093503 A1 · Language model tool calling and execution platform

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

- Number: US 2026/0093503 A1
- Document ID: US20260093503A1
- Status: Published application
- Kind: A1
- Application number: 19/356,111
- Filed: 2025-10-11
- Published: 2026-04-02
- Earliest claimed: 2024-10-01
- Assignees: Arcade Ai, Inc.
- Applicants: Arcade Ai, Inc.
- Inventors: SAMUEL HOLT PARTEE; Nathanael Robert BARBETTINI; Sterling Patrick DREYER; Alexander SALAZAR
- Web page: https://patentgrep.com/patent/US20260093503A1

## CPC

- G06F 16/33295: {in dialogue systems}
- G06N 20/00: Machine learning
- G06F 9/448: Execution paradigms, e.g. implementations of programming paradigms
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/08: Learning methods
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system for processing client requests in an AI ecosystem is provided. The system may receive a client request from a client application, where the client request is based upon a user request. The system may provide a model request, based upon the client request, to a first model (e.g., an LLM), receive, from the first model, a structured response based upon the model request, and cause execution of tool functions based upon the structured response.

## Claims

### Claim at position 1

1-59. (canceled)

### Claim 60

A system for authorizing requests, the system comprising:
a. one or more memories storing instructions; and
b. one or more processors, operably coupled to the one or more memories, for executing the instructions that cause the system to:
i. provide a model request, based upon a client request, to a first model of one or more models, wherein the client request is based upon a user request from a user;
ii. receive, from the first model, a structured response specifying one or more tool functions based upon the model request; and
1. for at least one tool function of the one or more tool functions:
a. if authorization is required for execution of the tool function by a corresponding service provider of one or more service providers:
i. provide, to a client application, information to enable access to the corresponding service provider; and
ii. receive an indication of access permission for access to the corresponding service provider,
iii. wherein the access permission indication enables execution of the tool function.

### Claim 61 (depends on 60)

The system of claim 60, wherein the information to enable access comprises an authorization URL.

### Claim 62 (depends on 60)

The system of claim 60, wherein the instructions, when executed, further cause the system to:
a. receive a second client request;
b. receive a second structured response from a third model of the one or more models, wherein the third model is the same as or different from the first model, and the second structured response is based upon the second client request; and
c. based upon the access permission indication, enable execution of the tool function based upon the second structured response.

### Claim 63 (depends on 60)

The system of claim 60, wherein the system further comprises a remote server, wherein receiving the access permission indication comprises receiving the access permission indication from a corresponding authorization provider via the remote server.

### Claim 64 (depends on 60)

The system of claim 60, wherein the access permission indication is received during a current session, and enables execution of the tool function based on a subsequent client request associated with the user.

### Claim 65 (depends on 60)

The system of claim 60, wherein the instructions, when executed, further cause the system to:
a. associate an access token with the access permission indication.

### Claim 66 (depends on 60)

The system of claim 60, wherein the instructions, when executed, further cause the system to:
a. cause execution of the tool function based upon the structure response and the access permission indication.

### Claim 67 (depends on 66)

The system of claim 66, wherein the instructions, when executed, further cause the system to:
a. provide a result of the execution to a second model of the one or more models, wherein the second model is the same as or different from the first model; and
b. receive a second result, based on the result, from the second model.

### Claim 68 (depends on 67)

The system of claim 67, wherein the instructions, when executed, further cause the system to:
a. provide the second result to the client application.

### Claim 69 (depends on 67)

The system of claim 67, wherein the second result comprises a natural language summary of the result.

### Claim 70

A method comprising:
a. providing a model request, based upon a client request, to a first model of one or more models, wherein the client request is based upon a user request from a user;
b. receiving, from the first model, a structured response specifying one or more tool functions based upon the model request; and
i. for at least one tool function of the one or more tool functions:
1. if authorization is required for execution of the tool function by a corresponding service provider of one or more service providers:
a. providing, to a client application, information to enable access to the corresponding service provider; and
b. receiving an indication of access permission for access to the corresponding service provider,
c. wherein the access permission indication enables execution of the tool function.

### Claim 71 (depends on 70)

The method of claim 70, wherein the information to enable access comprises an authorization URL.

### Claim 72 (depends on 70)

The method of claim 70, further comprising:
a. receiving a second client request;
b. receiving a second structured response from a third model of the one or more models, wherein the third model is the same as or different from the first model, and the second structured response is based upon the second client request; and
c. based upon the access permission indication, enabling execution of the tool function based upon the second structured response.

### Claim 73 (depends on 70)

The method of claim 70, wherein receiving the access permission indication comprises receiving the access permission indication from a corresponding authorization provider via a remote server.

### Claim 74 (depends on 70)

The method of claim 70, wherein the access permission indication is received during a current session, and enables execution of the tool function based on a subsequent client request associated with the user.

### Claim 75 (depends on 70)

The method of claim 70, further comprising:
a. associating an access token with the access permission indication.

### Claim 76 (depends on 70)

The method of claim 70, further comprising:
a. causing execution of the tool function based upon the structure response and the access permission indication.

### Claim 77 (depends on 76)

The method of claim 76, further comprising:
a. providing a result of the execution to a second model of the one or more models, wherein the second model is the same as or different from the first model; and
b. receiving a second result, based on the result, from the second model.

### Claim 78 (depends on 77)

The method of claim 77, further comprising:
a. providing the second result to the client application.

### Claim 79 (depends on 77)

The method of claim 77, wherein the second result comprises a natural language summary of the result.

### Claim 80

One of more non-transitory computer readable media comprising instructions that, when executed by at least one processor, cause a computer system to:
a. provide a model request, based upon a client request, to a first model of one or more models, wherein the client request is based upon a user request from a user;
b. receive, from the first model, a structured response specifying one or more tool functions based upon the model request; and
i. for at least one tool function of the one or more tool functions:
1. if authorization is required for execution of the tool function by a corresponding service provider of one or more service providers:
a. provide, to a client application, information to enable access to the corresponding service provider; and
b. receive an indication of access permission for access to the corresponding service provider,
c. wherein the access permission indication enables execution of the tool function.

### Claim 81 (depends on 70)

The non-transitory computer readable media of claim 70, wherein the information to enable access comprises an authorization URL.

### Claim 82 (depends on 70)

The non-transitory computer readable media of claim 70, wherein the instructions, when executed by at least one processor, further cause the computer system to:
a. receive a second client request;
b. receive a second structured response from a third model of the one or more models, wherein the third model is the same as or different from the first model, and the second structured response is based upon the second client request; and
c. based upon the access permission indication, enable execution of the tool function based upon the second structured response.

### Claim 83 (depends on 70)

The non-transitory computer readable media of claim 70, wherein receiving the access permission indication comprises receiving the access permission indication from a corresponding authorization provider via a remote server.

### Claim 84 (depends on 70)

The non-transitory computer readable media of claim 70, wherein the access permission indication is received during a current session, and enables execution of the tool function based on a subsequent client request associated with the user.

### Claim 85 (depends on 70)

The non-transitory computer readable media of claim 70, wherein the instructions, when executed by at least one processor, further cause the computer system to:
a. associate an access token with the access permission indication.

### Claim 86 (depends on 70)

The non-transitory computer readable media of claim 70, wherein the instructions, when executed by at least one processor, further cause the computer system to:
a. cause execution of the tool function based upon the structure response and the access permission indication.

### Claim 87 (depends on 76)

The non-transitory computer readable media of claim 76, wherein the instructions, when executed by at least one processor, further cause the computer system to:
a. provide a result of the execution to a second model of the one or more models, wherein the second model is the same as or different from the first model; and
b. receive a second result, based on the result, from the second model.

### Claim 88 (depends on 77)

The non-transitory computer readable media of claim 77, wherein the instructions, when executed by at least one processor, further cause the computer system to:
a. provide the second result to the client application.

### Claim 89 (depends on 77)

The non-transitory computer readable media of claim 77, wherein the second result comprises a natural language summary of the result.
