DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 05/26/2026 has been entered.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 05/26/2026 is being considered by the examiner.
Response to Amendment
The Amendment filed on 05/26/2026 has been entered. Claims 8 and 19 have been cancelled. Therefore, claims 1-7, 9-18, and 20-21 remain pending in the application.
Response to Arguments
Applicant’s arguments filed 05/26/2026 have been fully considered but they are not persuasive.
With respect to the 35 U.S.C. 101 rejection, on pages 12-13, the Applicant asserts that any alleged judicial exception is integrated into a practical application. They also assert that the amended limitations is not a judicial exception under the analysis of Step 2A, Prong One since it is not a certain method of organizing human activity, not a mathematical operation, and not a mental process. They further state that the additional elements is not a mental process since they are not possible to perform in the human mind even with the aid of pen and paper. They state that humans cannot execute semantic searches in computer data stores, and humans cannot append identifiers for a generative artificial intelligence model. They assert that the additional element integrates any alleged judicial exception into a practical application by improving a technical field, specifically artificial intelligence by providing a technical solution to the problem of computational bottlenecks that are inherent in large language models. This additional element allows the bottlenecks to be reduced or bypassed at least by using a semantic search to identify agents and then appending identifiers of the agents to the utterance to limit tokens used in the large language model.
The Examiner respectfully disagrees. The original claims, and the claims as amended, are merely utilizing computer devices, in this specific case “candidate agents”, “a first generative artificial intelligence model”, and “a second generative artificial intelligence model”, as tools to perform a method which is directed to an abstract idea. The claim, under its broadest reasonable interpretation, recites a method and system of receiving an utterance, writing an input prompt that includes incorporating API agents found based on a semantic similarity search for agents, writing a plan for completing requests found in the utterance that includes agents that were incorporated in the input prompt, creating an output for the plan that includes a list to complete the request, executing the plan by requesting action by the agents, getting the output from the agents, writing up a response to the original utterance that includes the output from the agents, and providing this response to the original utterance. Humans are very capable of performing semantic searches by understanding intent behind a request, as well as contextual meaning surrounding the request. The step of receiving a natural language utterance is insignificant data gather (or pre-solution activity), which is considered a generic computer input step. The addition of “data stores” is an insignificant extra-solution activity; pre-solutional activities do not provide an inventive concept. Human being are also able to utilize generic computer components, such as those mentioned above, to search through data stores. Humans are also very capable of appending text to a document, through pen and paper or through the use of a generic computer component. As far as improving the technical field of artificial intelligence by reducing or bypassing bottlenecks through a semantic search, while the claims do not need to explicitly recite the improvements shown in the Specification, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvements. Based on the plain reading of the amended claim, there is no reasonable improvement to the functioning of the generative artificial intelligence models used. Hence, Applicant’s arguments are not persuasive.
With respect to the 35 U.S.C. 103 rejection, pages 13-15, of claims 1-7, 9-18, and 20-21 under Liang et al. ("TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs", 03/29/2023), hereinafter referred to as Liang, in view of Lu et al. ("Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models", 05/24/2023), hereinafter referred to as Lu, the Applicant asserts that the combination of cited references does not disclose or make obvious each and every feature of amended claim 1. They further assert that Liang does not disclose “appending one or more identifiers of the one or more candidate agents to the natural language utterance such that a number of tokens generated for the input prompt remains under a token limit set for a first generative artificial intelligence model”. They also assert that Lu does not remedy these aforementioned deficiencies.
In response to Liang, in view of Lu, not disclosing or suggesting “appending one or more identifiers of the one or more candidate agents to the natural language utterance such that a number of tokens generated for the input prompt remains under a token limit set for a first generative artificial intelligence model”, Liang Figure 1 pg. 3 shows the API selector choosing the most relevant APIs, which is then fed back into the MCFM, which is then output in the form of an action sequence. This is performed conversationally, thereby implying that the previous results, i.e. the selected most relevant APIs, are included, or appended, to the input prompt (i.e. natural language utterance) and then included in the action sequence. Liang 4.1 pg. 17 also states: “We utilize ChatGPT as the MCFM in this scenario. The inputs to the MCFM include the API platform, conversational context, and general prompts.” All generative artificial intelligence models, specifically ChatGPT in this case, have maximum token limits for inputs because of memory limits, processing speed, and costs. This is a well-known and conventional measure taken within the art of artificial intelligence, and therefore would be an obvious inclusion. Hence, Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-7, 9-18, and 20-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Independent claims 1, 10, and 16 recite a method, system, and computer-readable medium (CRM), respectively. These claims therefore invoke a statutory category (machine and process) in Step 1 of the Subject Matter Eligibility Test.
Step 2A, Prong One: Independent claims 1, 10, and 16, under their broadest reasonable interpretation, recite a method, system, and CRM of receiving an utterance, writing an input prompt that includes incorporating API agents found based on a semantic similarity search for agents, writing a plan for completing requests found in the utterance that includes agents that were incorporated in the input prompt, creating an output for the plan that includes a list to complete the request, executing the plan by requesting action by the agents, getting the output from the agents, writing up a response to the original utterance that includes the output from the agents, and providing this response to the original utterance. These are abstract ideas in the form of certain methods of organizing human activity (i.e. mental processes such as observation, evaluation, judgement, and opinion). The steps of receiving data (i.e. an utterance), searching for data (i.e. API agents) based on a semantic similarity, writing a prompt that includes this found data, writing a plan to fulfill the data originally received, writing an output to the plan that includes a list, executing the plan to fulfill the data, and then responding to the original data with this executed output could be performed by a human using pen and paper or by purely mental reasoning.
Step 2A, Prong Two: The claims do not integrate the judicial exception into a practical application. The recitation of “candidate agents”, “a first generative artificial intelligence model”, and “a second generative artificial intelligence model” are generic instructions to perform the abstract idea on/using a computer and do not impose a meaningful limit on the judicial exception. The agents and generative artificial intelligence models are recited at such high-levels of generality and are merely used as tools to perform the abstract idea faster and more efficiently. The data receiving and outputting steps required to perform the method do not add a meaningful limitation. The steps of receiving data (i.e. an utterance) and outputting data (i.e. the response) are insignificant data gathering (or pre-solution activity) and outputting (or post-solution activity), which are generic computer steps. Mere data gathering, analysis, and output do not provide an inventive concept. There is no improvement to the functioning of creating a prompt for a generative artificial intelligence model, plan creation or generation, the functioning of the agents, the functioning of the artificial intelligence models, or to any other technology or technical field.
Step 2B: The claims do not include any additional elements that amount to significantly more than the judicial exception. The only additional elements beyond the abstract idea are the candidate agents and the generative artificial intelligence models, which perform generic computational functions such as receiving, analyzing, and outputting data. Such elements are well-understood, routine, and conventional within the field.
Accordingly, claims 1, 10, and 16 are directed to an abstract idea and do not include significantly more than the abstract idea itself.
With respect to claims 2, 11, and 17, the claims relate to creating an input prompt by conducting a semantic search for agents and including the agents in the prompt. This is a mental process that could be performed by a human using pen and paper or by purely mental reasoning. No additional elements are present.
With respect to claims 3 and 12, the claims relate to the utterance being conversational as well as the input prompt including the conversation. This is insignificant extra-solution activity; pre-solutional activities do not provide an inventive concept. Including the conversation into the input prompt could be performed by a human using pen and paper or by purely mental reasoning. No additional elements are present.
With respect to claims 4 and 13, the claims relate to the agents and the actions to fulfill, where the agents and actions are either prepared to be executed or first require more information. This is insignificant extra-solution activity; pre-solutional activities do not provide an inventive concept. No additional elements are present.
With respect to claims 5 and 14, the claims relate to executing the execution plan by obtaining more necessary information, requesting the agents to complete the actions, and including the necessary information within the request to the agents. This is a mental process that could be performed by a human using pen and paper or by purely mental reasoning. No additional elements are present.
With respect to claims 6 and 15, the claims relate to creating the execution plan where dependencies exist between the actions, creating an ordered list in order to complete the actions sequentially, or creating an execution plan to complete the actions in parallel. This is a mental process that could be performed by a human using pen and paper or by purely mental reasoning. No additional elements are present.
With respect to claims 7 and 18, the claims relate to the utterance being receiving in a conversation, and the response to the utterance includes the response and the conversation itself. This is a mental process that could be performed by a human using pen and paper or by purely mental reasoning. The only additional elements are “a chatbot” and “the second generative artificial intelligence model”, which are generic instructions to perform the abstract idea on/using a computer and do not impose a meaningful limit on the judicial exception. No additional elements are present.
With respect to claims 9 and 20, the claims relate to the first and second generative artificial intelligence models being the same model. This is insignificant extra-solution activity; pre-solutional activities do not provide an inventive concept. No additional elements are present.
With respect to claim 21, the claim relates to transmitting data to the agents to perform the requests of the utterance, and receiving this output from the agents. This is insignificant extra-solution activity; pre-solutional activities (including data transmission and output) do not provide an inventive concept. The only additional elements are “one or more agents” and “the second generative artificial intelligence model”, which are generic instructions to perform the abstract idea on/using a computer and do not impose a meaningful limit on the judicial exception. No additional elements are present.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-7, 9-18, and 20-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Liang et al. ("TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs", 03/29/2023), hereinafter referred to as Liang, in view of Lu et al. ("Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models", 05/24/2023), hereinafter referred to as Lu.
Regarding claim 1, Liang discloses a computer-implemented method comprising: receiving a natural language utterance (Liang Fig. 1 shows a user instruction from a conversational context being input into the multimodal conversational foundation model (MCFM));
constructing an input prompt comprising the natural language utterance (Liang Figure 1 pg. 3, user instruction is received by the multimodal conversational foundation model (MCFM) and Liang Figure 2 pg. 6, this instruction is dialogue based, i.e. a natural language instruction) by (i) executing a semantic search on descriptions associated with available agents in a data store to identify one or more candidate agents and (“The goal of API selector is to identify and select the most suitable APIs from API platform that fit the task requirement and solution outline as understood by MCFM. Since the API platform may have millions of APIs, the API selector needs the search capability to retrieve semantically relevant APIs,” Liang 2.4 pg. 4) (ii) appending one or more identifiers of the one or more candidate agents to the natural language utterance (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs, which is fed back into the MCFM, which is then output in the form of an action sequence, this continuation from previous results implies that the information previously presented stays added or appended to the input prompt) such that a number of tokens generated for the input prompt remains under a token limit set for a first generative artificial intelligence model (“We utilize ChatGPT as the MCFM in this scenario. The inputs to the MCFM include the API platform, conversational context, and general prompts,” Liang 4.1 pg. 17, all models have maximum token limits for inputs that they understand as their context window, ChatGPT’s changes depending on what version of it is being utilized);
generating, by [[ a ]] the first generative artificial intelligence model using the input prompt, an execution plan for executing one or more requests represented by the natural language utterance (Liang Figure 1 pg. 3, the MCFM outputs a solution outline),
wherein generating the execution plan comprises: determining, based on the one or more candidate (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline),
and generating a structured output for the execution plan by creating an ordered list [[ that ]] comprising
executing the execution plan to perform the one or more actions using the one or more agents (Liang Figure 1 pg. 3, the most relevant APIs are executed by calling APIs), wherein executing the execution plan comprises: triggering performance of the one or more actions by the one or more agents (Liang Figure 1 pg. 3, the most relevant APIs are executed by calling APIs), and receiving one or more outputs from performance of the one or more actions by the one or more agents ("After the execution, the action executor will return the results to users," Liang 2.5 pg. 4);
and providing the response ("After the execution, the action executor will return the results to users," Liang 2.5 pg. 4).
However, Liang fails to disclose generating, by a second generative artificial intelligence model using the one or more outputs, a response to the natural language utterance. Lu teaches a plug-and-play compositional reasoning framework to use external tools to address a broad range of tasks.
Lu teaches generating, by a second generative artificial intelligence model using the one or more outputs, a response to the natural language utterance (Pan Lu Figure 1 pg. 1, shows it is known within the art to use a generative AI model to generate final answers in a plan-based task execution system).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Liang’s method of completing tasks by connecting the main AI model to a multitude of APIs by including Lu’s method of using multiple models to complete various steps in a plan-based execution system. Using multiple different models that are specialized on specific tasks, in this case using a specific model to be the final answer generator for the requests, would improve the efficiency and accuracy of the process at each step, and thereby maximize the efficiency and accuracy of the system as a whole. This inclusion would have been obvious to one of ordinary skill in the art.
Regarding claim 2, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein constructing the input prompt comprises: executing, using the natural language utterance, a semantic search on descriptions associated with available agents and actions in a data store ("Since the API platform may have millions of APIs, the API selector needs the search capability to retrieve semantically relevant APIs," Liang 2.4 pg. 4 and "Each package corresponds to a specific domain," Liang 2.4 pg. 4);
identifying, based on a semantic search, the one or more candidate agents and associated actions ("Since the API platform may have millions of APIs, the API selector needs the search capability to retrieve semantically relevant APIs," Liang 2.4 pg. 4);
and constructing a natural language representation for the input prompt by appending the one or more candidate agents and associated actions to the natural language utterance (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs, which is fed back into the MCFM, which is then output in the form of an action sequence and "Next, MCFM generates action codes using the recommended APIs," Liang Figure 1 pg. 3).
Regarding claim 3, Liang, in view of Lu, discloses all of the limitations of claim 2. Liang further discloses wherein: the natural language utterance is a continuation or subsequent utterance within a conversation (Liang Figure 2 pg. 6, the user is having a dialogue (conversation) with the system),
the input prompt further comprises: (iii) conversation history and actions executed prior to the natural language utterance (Liang Figure 2 pg. 6, shows the user altering previous actions executed by the system and Liang 2.1 Formula (1) uses "the conversational context, denoted as C"), and
constructing the input prompt comprises accessing the conversation history and the actions executed prior to the natural language utterance, and constructing the natural language representation for the input prompt by appending the one or more candidate agents, the associated actions, and the conversation history and the actions executed prior to the natural language utterance to the natural language utterance (Liang Figure 2 pg. 6 shows the user having a dialogue and altering previous actions executed by the system and Liang Figure 1 pg. 3 shows the feedback being fed back into the MCFM, being then used to create the solution outline and thereby the action sequence. This implies that the conversation history and actions executed prior are used in creating future solution outlines and action sequences).
Regarding claim 4, Liang, in view of Lu, discloses all of the limitations of claim 3. Liang further discloses wherein: the one or more agents are a plurality of agents and the one or more actions are a plurality of actions (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline),
a first subset of the plurality of agents and the plurality of actions are in a first state and a second subset of the plurality of agents and the plurality of actions are in a second state (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline, this is dependent upon the specific APIs being called upon, and it is obvious and known within the art, as some APIs would require a login/registration before utilizing said API),
the first state is a ready-for-execution state, and the second state is a not-ready-for-execution state where additional information is required prior to execution of one or more actions within the second subset of the plurality of agents and the plurality of actions (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline, this is dependent upon the specific APIs being called upon, and it is obvious and known within the art, as some APIs would require a login/registration before utilizing said API).
Regarding claim 5, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein: executing the execution plan further comprises accessing contextual information that is needed by at least one of the one or more agents for performing at least one of the one or more actions (Liang Figure 1 pg. 3 shows conversational context being input to the MCFM, using that to generate the solution outline and thereby the action sequence);
triggering the performance of the one or more actions comprises forwarding one or more requests for performance of the one or more actions to the one the one or more agents (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline, implies calling upon the use of the selected APIs);
and a request of the one or more requests being forwarded for performance of the at least one of the one or more actions includes the contextual information (Liang Figure 1 pg. 3 shows conversational context being input to the MCFM, using that to generate the solution outline, which feeds into the API selector, and thereby generate the action sequence).
Regarding claim 6, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein: the one or more agents are a plurality of agents, the one or more actions are a plurality of actions, and the one or more requests are a plurality of requests (Liang Figure 1 pg. 3, the API selector chooses the most relevant APIs according to the solution outline steps where each API is associated with an action in the solution outline),
generating the execution plan further comprises determining whether one or more dependencies exist between the plurality of actions, and when the one or more dependencies exist, the ordered list is created to comprise the plurality of agents, the plurality of actions for executing the one or more requests, and an indication of the one or more dependencies ("Developers who offer a package of APIs could provide composition instructions. This can serve as guidance to the model on how to combine multiple APIs to accomplish complex user instructions," Liang 2.3 pg. 4),
when the execution plan comprises the indication of the one or more dependencies, the performance of the one or more actions by the one or more agents is triggered via serial processing ("Since this is a complex instruction, TaskMatrix.AI must break it down into roughly 25 API calls to complete the task," Liang 4.2 pg. 20 and Figure 11 pg. 18-19, these actions must inherently be ordered sequentially accordingly),
when the execution plan does not comprise the indication of the one or more dependencies, the performance of the one or more actions by the one or more agents is triggered via parallel processing ("TaskMatrix.AI uses an action executor to run various APIs, ranging from simple HTTP requests to complex algorithms or AI models that need multiple input parameters," Liang 2.5 pg. 4, it would be obvious to run APIs in parallel, as it is well-known in the art and would save time and computational power),
and the response is an aggregate response comprising a plurality of responses to the plurality of requests within the natural language utterance ("After the execution, the action executor will return the results to users," Liang 2.5 pg. 4, would be obvious to return the results to the plurality of requests).
Regarding claim 7, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein: the natural language utterance is received in a conversation with a chatbot (Liang Figure 2 pg. 6, the user is having a dialogue (conversation) with the system and Liang 2.1 Formula (1) uses "the conversational context, denoted as C" and Liang Fig. 1 shows a user instruction from a conversational context being input into the multimodal conversational foundation model (MCFM));
the natural language utterance is a continuation or subsequent utterance within the conversation (Liang Figure 2 pg. 6, the user is having a dialogue (conversation) with the system and Liang 2.1 Formula (1) uses "the conversational context, denoted as C");
the response to the natural language utterance is generated by the generative artificial intelligence model using the one or more outputs, the natural language utterance, and a conversation history for the conversation (Liang Figure 2 pg. 6, the user is having a dialogue (conversation) with the system and Liang 2.1 Formula (1) uses "the conversational context, denoted as C");
and the response is transmitted as a response from the chatbot ("After the execution, the action executor will return the results to users," Liang 2.5 pg. 4).
However, Liang does not disclose the second generative artificial intelligence model.
Lu teaches the second generative artificial intelligence model (Pan Lu Figure 1 pg. 1, shows it is known within the art to use a generative AI model to generate final answers in a plan-based task execution system).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Liang’s method of completing tasks by connecting the main AI model to a multitude of APIs by including Lu’s method of using multiple models to complete various steps in a plan-based execution system. Using multiple different models that are specialized on specific tasks, in this case using a specific model to be the final answer generator for the requests, would improve the efficiency and accuracy of the process at each step, and thereby maximize the efficiency and accuracy of the system as a whole. This inclusion would have been obvious to one of ordinary skill in the art.
Regarding claim 9, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein the first generative artificial intelligence model is the same model as the second generative artificial intelligence model (Liang Figure 1 pg. 3 shows the same model outputting a response).
As to claims 10-15, system claims 10-15 and method claims 1-6 are related as method and system of using same, with each claimed element’s function corresponding to the respective method step. Accordingly, claims 10-15 are similarly rejected under the same rationale as applied above with respect to the method claims.
As to claims 16-17, computer-readable medium (CRM) claims 16-17 and method claims 1-2 are related as method and CRM of using same, with each claimed element’s function corresponding to the respective method step. Accordingly, claims 16-17 are similarly rejected under the same rationale as applied above with respect to the method claims.
As to claim 18, CRM claim 18 and method claim 7 are related as method and CRM of using same, with each claimed element’s function corresponding to the method step. Accordingly, claim 18 is similarly rejected under the same rationale as applied above with respect to the method claim.
As to claim 20, CRM claim 20 and method claim 9 are related as method and CRM of using same, with each claimed element’s function corresponding to the method step. Accordingly, claim 20 is similarly rejected under the same rationale as applied above with respect to the method claim.
Regarding claim 21, Liang, in view of Lu, discloses all of the limitations of claim 1. Liang further discloses wherein the execution plan comprises computer-executable instructions (“It should be able to take multimodal inputs and contexts (such as text, image, video, audio, and code) and generate executable codes based on APIs that can complete specific tasks,” Liang pg. 3),
wherein executing the execution plan comprises executing the computer-executable instructions to: transmit data to the one or more agents to facilitate performance of the one or more actions to generate data to provide to the generative artificial intelligence model (Liang Fig. 8 shows a conversational chatbot requesting extra data to perform the user’s requests);
and receive the one or more outputs from the performance of the one or more actions by the one or more agents ("After the execution, the action executor will return the results to users," Liang 2.5 pg. 4).
However, Liang does not disclose the second generative artificial intelligence model.
Lu teaches the second generative artificial intelligence model (Pan Lu Figure 1 pg. 1, shows it is known within the art to use a generative AI model to generate final answers in a plan-based task execution system).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Liang’s method of completing tasks by connecting the main AI model to a multitude of APIs by including Lu’s method of using multiple models to complete various steps in a plan-based execution system. Using multiple different models that are specialized on specific tasks, in this case using a specific model to be the final answer generator for the requests, would improve the efficiency and accuracy of the process at each step, and thereby maximize the efficiency and accuracy of the system as a whole. This inclusion would have been obvious to one of ordinary skill in the art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US Patent Application Publication No. 2024/0419487
US Patent Application Publication No. 2025/0086439
Shen et al., “HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face”, 05/25/2023
Song et al., “RestGPT: Connecting Large Language Models with Real-World RESTful APIs”, 08/27/2023
Qin et al., “TOOLLLM: FACILITATING LARGE LANGUAGE MODELS TO MASTER 16000+ REAL-WORLD APIS”, 09/03/2023
Ning et al., “SKELETON-OF-THOUGHT: LARGE LANGUAGE MOD ELS CAN DO PARALLEL DECODING”, 09/08/2023
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ADAM MICHAEL WEAVER whose telephone number is (571)272-7062. The examiner can normally be reached Monday-Friday, 8AM-5PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richemond Dorvil can be reached at (571) 272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ADAM MICHAEL WEAVER/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658
Prosecution Insights