# US 2026/0073256 A1 · Enhancing reasoning capabilities in a vision language model (vlm) with generative flow networks (gflownets)

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

- Number: US 2026/0073256 A1
- Document ID: US20260073256A1
- Status: Published application
- Kind: A1
- Application number: 19/322,644
- Filed: 2025-09-08
- Published: 2026-03-12
- Earliest claimed: 2024-09-09
- Assignees: Honda Motor Co., Ltd.
- Applicants: Honda Motor Co., Ltd.
- Inventors: Haoqiang KANG; Enna SACHDEVA; Piyush GUPTA; Sangjae BAE; Kwonjoon LEE
- Web page: https://patentgrep.com/patent/US20260073256A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

According to one aspect, enhancing reasoning capabilities in a vision language model (VLM) with generative flow networks (GFlowNets) may include generating a chain of thought (CoT) reasoning and an action for a first time-step based on a vision language model (VLM), an input observation image, and an input text prompt, generating an action space for a second time-step and a sequence of transitions based on a simulation environment, the CoT, and the action for the first time-step, and fine-tuning the VLM based on updating a forward policy of a generative flow network (Gflownet) based on buffering the sequence of transitions and one or more losses.

## Claims

### Claim 1

A system for enhancing reasoning capabilities in a vision language model (VLM) with generative flow networks (GFlowNets), comprising:
a memory storing one or more instructions; and
a processor executing one or more of the instructions stored on the memory to perform:
generating a chain of thought (CoT) reasoning and an action for a first time-step based on a vision language model (VLM), an input observation image, and an input text prompt;
generating an action space for a second time-step and a sequence of transitions based on a simulation environment, the CoT, and the action for the first time-step; and
fine-tuning the VLM based on updating a forward policy of a generative flow network (Gflownet) based on buffering the sequence of transitions and one or more losses.

### Claim 2 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, comprising a sensor sensing the input observation image.

### Claim 3 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein the input text prompt includes a goal description, a history of states, a history of actions, and the action space.

### Claim 4 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein the VLM includes an encoder and a projector generating a vision encoding for the VLM based on the input observation image.

### Claim 5 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein the VLM includes a text tokenizer generating a text token for the VLM based on the input text prompt.

### Claim 6 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein the simulation environment executes the action to generate a reward, an observation at the second time-step, and the action space for the second time-step.

### Claim 7 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein the processor generates a text prompt for the second time-step based on a function, a history of states, a history of actions, the action space for a second time-step, and an observation at the second time-step.

### Claim 8 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein one or more of the losses is a Variance Trajectory-Balanced (TB) loss that ensures a probability of generating a complete trajectory is proportional to a reward.

### Claim 9 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein one or more of the losses is a Subtrajectory-Balanced (SubTB) loss that ensures a segment of a CoT reasoning path remains consistent.

### Claim 10 (depends on 1)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 1, wherein one or more of the losses is a Detailed Balanced (DB) loss that ensures that a transition between a first state and a second state is balanced by matching a forward flow and a backward flow at each step of a trajectory.

### Claim 11

A computer-implemented method for enhancing reasoning capabilities in a vision language model (VLM) with generative flow networks (GFlowNets), comprising:
generating a chain of thought (CoT) reasoning and an action for a first time-step based on a vision language model (VLM), an input observation image, and an input text prompt;
generating an action space for a second time-step and a sequence of transitions based on a simulation environment, the CoT, and the action for the first time-step; and
fine-tuning the VLM based on updating a forward policy of a generative flow network (Gflownet) based on buffering the sequence of transitions and one or more losses.

### Claim 12 (depends on 11)

The computer-implemented method for enhancing reasoning capabilities in the VLM with GFlowNets of claim 11, wherein the input text prompt includes a goal description, a history of states, a history of actions, and the action space.

### Claim 13 (depends on 11)

The computer-implemented method for enhancing reasoning capabilities in the VLM with GFlowNets of claim 11, wherein one or more of the losses is a Variance Trajectory-Balanced (TB) loss that ensures a probability of generating a complete trajectory is proportional to a reward.

### Claim 14 (depends on 11)

The computer-implemented method for enhancing reasoning capabilities in the VLM with GFlowNets of claim 11, wherein one or more of the losses is a Subtrajectory-Balanced (SubTB) loss that ensures a segment of a CoT reasoning path remains consistent.

### Claim 15 (depends on 11)

The computer-implemented method for enhancing reasoning capabilities in the VLM with GFlowNets of claim 11, wherein one or more of the losses is a Detailed Balanced (DB) loss that ensures that a transition between a first state and a second state is balanced by matching a forward flow and a backward flow at each step of a trajectory.

### Claim 16

A system for enhancing reasoning capabilities in a vision language model (VLM) with generative flow networks (GFlowNets), comprising:
a memory storing one or more instructions; and
a processor executing one or more of the instructions stored on the memory to perform:
generating a chain of thought (CoT) reasoning and an action for a first time-step based on a vision language model (VLM), an input observation image, and an input text prompt; and
generating an action space for a second time-step and a sequence of transitions based on a simulation environment, the CoT, and the action for the first time-step,
wherein the VLM is fine-tuned during a training stage based on updating a forward policy of a generative flow network (Gflownet) based on buffering the sequence of transitions from the training stage and one or more losses.

### Claim 17 (depends on 16)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 16, wherein the input text prompt includes a goal description, a history of states, a history of actions, and the action space.

### Claim 18 (depends on 16)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 16, wherein one or more of the losses is a Variance Trajectory-Balanced (TB) loss that ensures a probability of generating a complete trajectory is proportional to a reward.

### Claim 19 (depends on 16)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 16, wherein one or more of the losses is a Subtrajectory-Balanced (SubTB) loss that ensures a segment of a CoT reasoning path remains consistent.

### Claim 20 (depends on 16)

The system for enhancing reasoning capabilities in the VLM with GFlowNets of claim 16, wherein one or more of the losses is a Detailed Balanced (DB) loss that ensures that a transition between a first state and a second state is balanced by matching a forward flow and a backward flow at each step of a trajectory.
