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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 22 July 2026 has been entered.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-15 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 63/443,602, fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application. For example, with respect to claim 1, Application No. 63/443,602 does not disclose anything regarding an LLM agent memory, or the particular requirements of the retrieving step (c) recited in claim 1. Independent claims 5 and 9 recite similar limitations that are not supported by Application No. 63/443,602.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Park et al. (Generative Agents: Interactive Simulacra of Human Behavior, hereinafter “Park”).
In regard to claim 1, Park discloses a method for determining a prediction of a population level response to presented information (multi-agent simulation of human behavior, Abstract), comprising:
(a) conditioning at least one large language model (LLM) agent on a plurality of population or group features using in-weight training or in-context tokens (an LLM agent is conditioned with a natural language prompt describing the agent’s identity, section 3.1);
(b) recording an initial memory state of the at least one LLM agent (each phrase is entered into the agent’s initial memory, section 3.1);
(c) retrieving one or more entries of an output of the at least one LLM agent from an LLM agent memory based on a cosine similarity between a current internal state of the at least one LLM agent and the LLM agent memory to include in the next planning step (at each time step, an agent’s behavior is determined based on past experience and mixed with the agent’s current context and plans, section 2.3, final paragraph; each agent comprises a memory stream where memories are retrieved based on a cosine similarity between the memories and the agent’s planning, section 4.1), wherein the current internal state comprises a current reflection of the at least one LLM agent (memories include reflection, section 4.2), one or more conditioned intra-agent communications (an agent’s dialog is determined based on summarized memories of prior interactions with other agents, section 4.3.2), and a compressed global state (the memory stream comprises a compressed record of the agent’s past experience, section 4);
(d) planning a response of the at least one LLM agent to an environment for the presented information (agents generate behavior in response to situational information based on plans, section 4.3 and 4.3.2);
(e) transmitting the one or more conditioned intra-agent communications to a plurality of additional LLM agents (agents converse with each other to exchange information, section 4.3.2; and information diffuses between agents in a plurality of communications, section 3.4.1);
(f) receiving the one or more conditioned intra-agent communications from the plurality of additional LLM agents (agents receive communications from other agents, section 4.3.2 and section 3.4.1);
(g) recording an updated memory state of the LLM agent based on the one or more sent and received conditioned intra-agent communications (agents update relationship memory based on conversations with other agents, section 3.4.2 and section 4.3.2); and
(h) generating the prediction based on the updated memory state (test and prototype of social systems and theories, section 8.1).
In regard to claim 2, Park discloses the prediction comprises an election outcome (election simulation, section 3.1.1).
In regard to claim 3, Park discloses the plurality of additional LLM agents are defined by the environment for the information (agents are instantiated in a sandbox environment, section 5).
In regard to claim 4, Park discloses iterating procedures (a)-(h) for one or more additional time points (the agent behavior is simulated at each time step, section 5).
In regard to claim 5, Park discloses a system for determining a prediction of a population level response to presented information (a server, section 5), comprising:
at least one computer processor (a server inherently includes a processor, section 5) configured to:
(a) condition at least one large language model (LLM) agent on a plurality of population or group features using in-weight training or in-context tokens (an LLM agent is conditioned with a natural language prompt describing the agent’s identity, section 3.1);
(b) record an initial memory state of the at least one LLM agent (each phrase is entered into the agent’s initial memory, section 3.1);
(c) retrieve one or more entries of an output of the at least one LLM agent from an LLM agent memory based on a cosine similarity between a current internal state of the at least one LLM agent and the LLM agent memory to include in the next planning step (at each time step, an agent’s behavior is determined based on past experience and mixed with the agent’s current context and plans, section 2.3, final paragraph; each agent comprises a memory stream where memories are retrieved based on a cosine similarity between the memories and the agent’s planning, section 4.1), wherein the current internal state comprises a current reflection of the at least one LLM agent (memories include reflection, section 4.2), one or more conditioned intra-agent communications (an agent’s dialog is determined based on summarized memories of prior interactions with other agents, section 4.3.2), and a compressed global state (the memory stream comprises a compressed record of the agent’s past experience, section 4);
(d) plan a response of the at least one LLM agent to an environment for the presented information (agents generate behavior in response to situational information based on plans, section 4.3 and 4.3.2);
(e) transmit the one or more conditioned intra-agent communications to a plurality of additional LLM agents (agents converse with each other to exchange information, section 4.3.2; and information diffuses between agents in a plurality of communications, section 3.4.1);
(f) receive the one or more conditioned intra-agent communications from the plurality of additional LLM agents (agents receive communications from other agents, section 4.3.2 and section 3.4.1);
(g) record an updated memory state of the LLM agent based on the one or more sent and received conditioned intra-agent communications (agents update relationship memory based on conversations with other agents, section 3.4.2 and section 4.3.2); and
(h) generate the prediction based on the updated memory state (test and prototype of social systems and theories, section 8.1).
In regard to claim 6, Park discloses the prediction comprises an election outcome (election simulation, section 3.1.1).
In regard to claim 7, Park discloses the plurality of additional LLM agents are defined by the environment for the information (agents are instantiated in a sandbox environment, section 5).
In regard to claim 8, Park discloses iterating procedures (a)-(h) for one or more additional time points (the agent behavior is simulated at each time step, section 5).
In regard to claim 9, Park discloses a computer accessible medium which includes software thereon for determining a prediction of a population level response to presented information (data structure used by server, section 5), wherein, when at least one computer processor executes the software, the computer processor is configured to perform the procedures (a server which inherently comprises a processor, section 5), comprising
(a) conditioning at least one large language model (LLM) agent on a plurality of population or group features using in-weight training or in-context tokens (an LLM agent is conditioned with a natural language prompt describing the agent’s identity, section 3.1);
(b) recording an initial memory state of the at least one LLM agent (each phrase is entered into the agent’s initial memory, section 3.1);
(c) retrieving one or more entries of an output of the at least one LLM agent from an LLM agent memory based on a cosine similarity between a current internal state of the at least one LLM agent and the LLM agent memory to include in the next planning step (at each time step, an agent’s behavior is determined based on past experience and mixed with the agent’s current context and plans, section 2.3, final paragraph; each agent comprises a memory stream where memories are retrieved based on a cosine similarity between the memories and the agent’s planning, section 4.1), wherein the current internal state comprises a current reflection of the at least one LLM agent (memories include reflection, section 4.2), one or more conditioned intra-agent communications (an agent’s dialog is determined based on summarized memories of prior interactions with other agents, section 4.3.2), and a compressed global state (the memory stream comprises a compressed record of the agent’s past experience, section 4);
(d) planning a response of the at least one LLM agent to an environment for the presented information (agents generate behavior in response to situational information based on plans, section 4.3 and 4.3.2);
(e) transmitting the one or more conditioned intra-agent communications to a plurality of additional LLM agents (agents converse with each other to exchange information, section 4.3.2; and information diffuses between agents in a plurality of communications, section 3.4.1);
(f) receiving the one or more conditioned intra-agent communications from the plurality of additional LLM agents (agents receive communications from other agents, section 4.3.2 and section 3.4.1);
(g) recording an updated memory state of the LLM agent based on the one or more sent and received conditioned intra-agent communications (agents update relationship memory based on conversations with other agents, section 3.4.2 and section 4.3.2); and
(h) generating the prediction based on the updated memory state (test and prototype of social systems and theories, section 8.1).
In regard to claim 10, Park discloses the prediction comprises an election outcome (election simulation, section 3.1.1).
In regard to claim 11, Park discloses the plurality of additional LLM agents are defined by the environment for the information (agents are instantiated in a sandbox environment, section 5).
In regard to claim 12, Park discloses iterating procedures (a)-(h) for one or more additional time points (the agent behavior is simulated at each time step, section 5).
In regard to claims 13-15, Park discloses the one or more entries comprise LLM agent outputs from a current time step or a prior time step (the memory stream comprises information from current and prior time steps, section 4.1).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Hradec et al., Kalya et al., Vezhnevets et al., Li et al., Hatalis et al., and Sanders et al. disclose additional generative agent applications. Busch et al., Patel, Huberman et al., and Kumar et al. disclose additional methods of making predictions based on populations. Kim et al. and Doggett et al. disclose additional virtual agents that utilize a cosine similarity to retrieve memories.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN LOUIS ALBERTALLI whose telephone number is (571)272-7616. The examiner can normally be reached M-F 8AM-3PM, 4PM-5PM.
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, Bhavesh Mehta can be reached at 571-272-7453. 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.
BLA 9/2/26
/BRIAN L ALBERTALLI/ Primary Examiner, Art Unit 2656
Prosecution Insights