MindVoyager: Exploratory Research Framework

• MindVoyager is a framework that facilitates structured exploration in synthetic data generation and LLM therapist evaluation, emphasizing global diversity and latent cognition uncovering.
• It employs a determinantal point process to iteratively select outputs, combining explorer prompts and an anchor set to maximize diversity without accessing LLM weights.
• Empirical results reveal significant improvements in diversity scores (up to 412% over defaults) and enhanced data efficiency, with extensions to multimodal and immersive applications.

MindVoyager designates several recent research usages organized around exploration under partial observability. In the supplied literature, the name refers most directly to a training-free, iterative framework for generating synthetic datasets with much higher diversity from an LLM, and to a controllable evaluation framework for LLM therapists that tests whether hidden beliefs, thoughts, and histories can be uncovered over the course of counseling. Related systems, including VoyagerVision for multimodal Minecraft building and VIVRA for VR-based visualization of verbalized ideas, illuminate adjacent multimodal and embodied extensions of the same exploratory motif (Amballa et al., 12 Dec 2025, Kim et al., 25 Jul 2025, Smyth et al., 29 Jun 2025, Xing et al., 2024).

1. Scope of the term

The supplied literature uses MindVoyager in more than one technical sense. One usage concerns synthetic data generation, where the objective is global dataset diversity rather than local sampling variability. Another concerns therapist evaluation, where the objective is exploration of a client’s latent cognitive structure rather than surface conversational quality. Adjacent works do not always use the exact same name, but they preserve a closely related architecture of iterative perception, critique, and refinement.

Usage	Domain	Core construct
MindVoyager	Synthetic dataset generation	DPP-based volume maximization with explorers and an anchor set
MindVoyager	LLM therapist evaluation	Cognitive diagram, controllable openness and metacognition, cognition mediator
VoyagerVision	Embodied multimodal agent	Screenshot-augmented curriculum, action, and critic agents
VIVRA	VR reflection and ideation	Speech transcription, LLM topic extraction, interactive 3D idea balloons

This suggests that MindVoyager is best understood not as a single standardized architecture, but as a family of research instantiations centered on structured exploration: of semantic output space, of human cognition, or of embodied environments.

2. MindVoyager as a framework for diverse synthetic dataset generation

In the synthetic-data setting, MindVoyager addresses the claim that standard LLM sampling and prompt-based generation often produce many near-duplicates or semantically clustered outputs, so the resulting synthetic datasets have limited coverage of the underlying data manifold. The framework therefore aims to generate a dataset that is not just large, but globally diverse. The paper argues that prior methods fail for structural reasons: temperature, nucleus/top-p, min-p, etc. only perturb the next-token distribution; prompt-based diversity control may require domain knowledge and may diversify only along pre-chosen axes; and training-based diversity optimization requires access to weights and post-training, making it unsuitable for black-box LLMs.

Its central formal device is the determinantal point process. For a set $S$ and kernel matrix $K$, the objective is

$$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$

where $K_S$ is the submatrix indexed by $S$. The determinant of the similarity matrix is interpreted as the squared volume spanned by the representations of a set of points, so larger volume implies that the points are more spread out and less redundant. When a candidate item $w$ is considered relative to an anchor set $A$, the marginal diversity gain is

$$\gamma = \frac{\det(\mathbf{S'})}{\det(\mathbf{S})},$$

with $\mathbf{S}=K(A)$ and $\mathbf{S'}=K(A\cup\{w\})$. The candidate is accepted if $K$0.

The algorithm maintains two evolving structures: Explorers $K$1, which are prompts that guide generation, and an Anchor set $K$2, which is a fixed-size representative memory of diverse accepted examples. Its inputs are a task prompt $K$3, target dataset size $K$4, marginal gain threshold $K$5, max number of explorers per step $K$6, anchor set size $K$7, and max iterations $K$8. It initializes $K$9, $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$0, and $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$1. For each explorer, it calls the LLM once through Explore(e, Φ, τ, K_sim), obtains a batch $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$2 of candidate instances, filters each candidate by the marginal gain criterion, adds accepted items to the dataset and anchor pool, and places rejected samples in a rejected set $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$3.

If rejected samples exist, the framework performs two further LLM-mediated operations. One call produces textual gradients, described as textual critiques that explain why the outputs were not diverse enough. A subsequent call applies those textual gradients to edit the explorer prompt and produce successor explorers $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$4. Because the anchor set may grow too large, it is compressed back to size $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$5 using SampleDPP(A, k, K_a). The next explorers are also selected through a DPP over explorer similarity, with at most $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$6 explorers retained for the next round. The process continues until the dataset reaches size $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$7 or the iteration limit $$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$8 is reached.

A major property of the framework is that it does not require logits, gradients, or weights from the underlying LLM. It requires only prompt access, generated text outputs, and a similarity kernel computed externally from embeddings or text features. The experiments use a convex combination of an RBF kernel over text embeddings and a Jaccard lexical similarity kernel, with weights 0.7 and 0.3 respectively; text embeddings are from OpenAI’s text-embedding-3-small, and generation uses [GPT-4o](https://www.emergentmind.com/topics/vocabulary-assistant-llm-gpt-4o) mini. Scalability is obtained by keeping a fixed-size anchor set and a small explorer beam rather than sampling a huge universe and then running a global DPP on the entire dataset. The reported complexity is roughly

$$\mathbb{P}(S \sim \mathrm{DPP}(K)) \propto \det(K_S),$$9

with marginal gain computable in about $K_S$0 if cached inverses are used, and with estimated average outer iterations

$K_S$1

where $K_S$2 is the acceptance fraction (Amballa et al., 12 Dec 2025).

3. Empirical profile of the dataset-generation formulation

The evaluation spans two categories. Creative writing includes sentence generation about sports, short conversation about politics, poem generation, and movie plot generation. Reasoning includes grade school math question generation and simple logic puzzle generation. Baselines are Default, Temp, Diverse, History, Hierarchical, and SubsetSelect. Metrics are Lexical distance as mean Jaccard distance over pairs, Cosine distance as mean embedding cosine distance, Vendi score as a diversity score based on effective rank / spectrum, Quality as an LLM-as-judge rubric score, and LLM calls as efficiency / cost (Amballa et al., 12 Dec 2025).

Across all tasks, MindVoyager is reported to achieve the highest diversity scores. For creative tasks, the reported average improvements are 296% over Default and 43% over Hierarchical. For reasoning tasks, the reported average improvements are 412% over Default and 102% over Hierarchical. The paper also summarizes the effect more conservatively as roughly a 1.5–3x improvement in diversity in the main text, while noting much larger gains on some tasks when measured by Vendi. Quality generally does not degrade significantly, and in some cases it improves.

Task	MindVoyager Vendi	Default Vendi
Sports	24.132	2.991
Politics	15.035	4.589
Poem	7.312	3.004
Movie	8.302	4.002
Math	18.777	3.039
Logic puzzle	13.256	3.312

The ablations clarify which components drive the gains. If the next explorers are sampled randomly instead of via DPP, diversity drops, quality drops slightly, and more LLM calls are needed; this is taken to support the claim that diverse explorers improve search efficiency. If prompt refinement by textual gradients is removed, rejection rates rise, the algorithm needs more iterations, and convergence slows. The framework is also evaluated as a synthetic training-data generator: with 1000 GSM8K-style questions, answers obtained by GPT-4 few-shot prompting, and training on Gemma-2B-IT and Gemma-7B-IT, the MindVoyager-generated data yields higher downstream accuracy than training on the same amount of default-generated data. A reported example is 45.7 for Gemma-7B-IT versus 35.7 with default data, and the paper further notes that 500 MindVoyager examples can nearly match or exceed default-baseline training with 1000 examples, suggesting higher data efficiency.

The limitations are explicit. The framework is only evaluated on text generation, relies mostly on automated metrics rather than extensive human evaluation, still requires multiple LLM calls and may therefore be costlier than naive one-shot prompting, and depends on a reasonable similarity kernel and threshold $K_S$3. The practical heuristic for initializing $K_S$4 is also specified: sample 100 outputs, DPP-select 10, set $K_S$5 proportional to the determinant of that subset, and optionally decay $K_S$6 over time. A common misconception addressed by the paper is that higher-temperature sampling is sufficient for diversity; the framework’s claim is precisely that local next-token perturbation does not enforce global semantic non-redundancy (Amballa et al., 12 Dec 2025).

4. MindVoyager as an evaluation framework for LLM therapists

In the counseling literature, MindVoyager is an evaluation framework designed to test whether an LLM therapist can uncover inner states that are not immediately disclosed. Its point of departure is the observation that many existing client simulators are too fluent, cooperative, and reflective, so the therapist never has to elicit hidden beliefs. The framework therefore focuses on the exploration stage of counseling, where the therapist and client collaboratively uncover emotions, automatic thoughts, beliefs, coping strategies, and relevant past experiences. The motivating diagnosis is that real clients vary in openness and metacognition, whereas prompting-only simulators do not instantiate these constraints faithfully. Reported numbers are explicit: prompt-engineered GPT-4o-mini simulators still averaged 4.28 openness and 4.15 metacognition on a 1–5 scale, and when prompted to be realistic they reached 5.0 on both. Over 20 sessions, therapist-expert feedback identified the largest discrepancies from real clients as self-awareness, openness to share experiences, openness to suggestions, and rapid emotional transition.

The framework is built around a structured graph of client cognition called a cognitive diagram, inspired by the CBT Cognitive Conceptualization Diagram (CCD). It defines

$K_S$7

where $K_S$8 is the external cognitive diagram and $K_S$9 is the internal cognitive diagram. The external diagram contains situations, automatic thoughts, emotions, and behaviors. The internal diagram contains relevant histories, core beliefs, intermediate beliefs, and coping strategies. The appendix describes the full CCD-inspired structure as eight interconnected components: relevant history, core beliefs, intermediate beliefs, coping strategies, situations, automatic thoughts, emotions, and behaviors.

At session start, all internal elements are initially masked, and only a portion of the external diagram is accessible. Initialization is governed by openness, which determines how many external elements are initially accessible, and metacognition, which determines how quickly internal elements can be recognized and verbalized. Dynamic adaptation is handled by a cognition mediator, which repeatedly asks two questions: Has rapport been established? and Has the therapist helped the client explore themselves? The rapport update is formalized as

$S$0

followed, on success, by

$S$1

so that the accessible portion of the external diagram increases. The exploration update is

$S$2

and when successful, internal elements are gradually revealed.

The appendix specifies the operational settings. The mediator uses GPT-4o-mini with temperature 0.3. Openness is checked every 4 turns; if the rapport score is 4 or higher, openness increases and one additional situation is revealed, up to a maximum of three. Metacognition is checked every 2 turns for low-metacognition clients and every turn for high-metacognition clients; if the question-facilitating critic scores 4 or higher, internal cognition is revealed. Client responses are then generated by GPT-4o-mini at temperature 0.3, with instructions to remain vague or defensive when rapport is low, disclose more gradually as rapport increases, avoid abruptly revealing core beliefs or histories, and let deeper beliefs emerge naturally rather than explicitly naming them.

The framework introduces two dedicated exploration metrics. Cognitive Diagram Exposure Rate (CDER) is a binary session-level metric: a session counts as success only if the therapist reveals every element of the initially masked cognitive diagram. Induced Diagram Similarity Score (IDSS) measures whether the internal diagram inferred from the counseling session is semantically aligned with the ground-truth internal diagram. The appendix states that cognitive elements are extracted using an automated semantic parser and compared using LLM-based embeddings, specifically text-embedding-ada-002 and cosine similarity. Evaluated therapist models are GPT-4o, GPT-4o-mini, Llama-3.1-8B, Llama-3.1-70B, Claude-3.5-Haiku, and Camel, a 7B CBT-based counseling model fine-tuned on psychological counseling data. The three difficulty settings are easy, normal, and hard, corresponding to different openness and metacognition configurations; the appendix states easy uses high openness and high metacognition with $S$3 and $S$4, hard uses low openness and low metacognition with $S$5 and $S$6, the maximum number of turns is 15, and the conversation ends if the therapist says “goodbye” (Kim et al., 25 Jul 2025).

5. Empirical findings in therapist evaluation

The simulator itself is validated against prompt-based GPT-4o-mini client simulation and Patient-v. The evaluation constructs 100 personas grouped by openness and metacognition: low/low, low/high, high/low, and high/high. For human-likeness assessment, GPT-4-based A/B comparisons are used, order is alternated to control positional bias, and ties are allowed. Against the prompt baseline, the simulator wins 88/100, with 0 losses and 12 ties. Against Patient-v, human experts prefer the new simulator with reported win rates of 72% for easy, 82% for normal, and 92% for hard. These numbers are presented as evidence that dynamic openness and metacognition produce more human-like and more challenging clients (Kim et al., 25 Jul 2025).

On the therapist-evaluation task, the major conclusion is that exploration becomes harder as difficulty rises, and that internal cognition is substantially harder to uncover than external cognition. Reported examples from the CDER table include GPT-4o-mini dropping from 91.84 on easy to 72.45 on normal and 61.22 on hard; GPT-4o declining from 65.31 to 53.06 to 44.90; and Camel moving from 77.55 to 72.45 to 55.10. The paper notes that Llama-3.1-70B performs best in CDER overall. For IDSS, Llama-3.1-70B and Claude-3.5-Haiku are reported as the strongest models, while GPT models show mixed behavior. The interpretive claim is that getting a client to speak is not equivalent to inducing semantically correct disclosure of core beliefs, histories, or coping strategies.

The strategy analysis provides a more granular account of what successful exploration looks like. The paper uses 13 therapeutic strategies grouped into questions, reflections, solutions, and others, and finds that questioning, especially deep questions, is most important for exploration. Reflection on emotions is highly common across models. Llama-3.1-8B and Camel show similar strategy distributions, which the paper attributes to Camel’s basis in Llama-3.1-8B. A separate adaptability analysis, using cosine similarity of strategy usage across client types, reports that GPT-4o, Camel, and Llama-3.1-8B show more dynamic adaptation; Claude-3.5-Haiku shows the least flexibility; and GPT-4o-mini and Llama-3.1-70B are intermediate.

A central controversy addressed by the framework concerns evaluation validity. The paper compares CDER and IDSS with the Cognitive Therapy Rating Scale (CTRS) and finds that the new metrics are only slightly correlated with CTRS, but not directly related. The implication drawn in the paper is that a therapist can score reasonably on conventional counseling-quality measures while remaining weak at exploration. This separates empathic tone or session quality from the narrower and more psychologically specific task of uncovering latent cognitive structure (Kim et al., 25 Jul 2025).

6. Multimodal and embodied adjacencies

The broader exploratory design space is clarified by two adjacent systems. VoyagerVision is a multimodal extension of Voyager for Minecraft. It retains the three-agent structure of curriculum agent, action agent, and critic agent, but augments each with screenshot input and switches the backbone model to GPT-4o. The curriculum agent chooses tasks using environment state plus a screenshot of the agent’s point of view; the action agent generates Mineflayer JavaScript code conditioned on the same state, screenshot, task, critique, and code/error history; and the critic agent uses the screenshot as its primary evidence for spatial and building tasks. A skill library is retained for reuse and composition. The task loop is explicit: task proposal, code generation, code execution, critic verification, success logging and skill storage on success, or feedback and retry on failure, with a maximum of 3 attempts per task. In unit tests, five structures—pole, wall, stairs, portal, and pyramid—are each attempted 10 times, with 5 attempts in a superflat world and 5 in a regular world. Reported build success rates are 13(12)/25 in flat worlds, 7(6)/25 in regular worlds, and 20(18)/50 overall, where the number outside parentheses is critic-reported success and the number inside is true success after manual checking. In open-ended evaluation across 12 runs, VoyagerVision completes an average of 2.75 unique building tasks within 50 iterations, with overall average success rate on building tasks of 39% and average unique structures successfully created of 2.75. The paper also reports that screenshots do not significantly change resource-gathering performance, but they do enable building tasks that the original Voyager could not robustly handle (Smyth et al., 29 Jun 2025).

VIVRA is a room-scale immersive VR application combining multimodal interaction with LLMs to transform users’ ideas into interactive 3D “idea balloons.” In the supplied summary it is framed as a “MindVoyager”-style VR/LLM system. Its pipeline consists of real-time speech capture and transcription through Microsoft Azure Speech-to-Text, prompt construction from the current transcript and existing topics, topic extraction and summarization by ChatGPT (GPT-3.5-turbo), and VR visualization of each topic as a floating balloon that can be viewed, edited, deleted, added to, merged, and repositioned via voice, gaze, and VR controllers. Balloons are transparent with $S$7, move upward over time to encode temporal order, and grow linearly by number of words in the associated transcript, with growth stopping after 300 words. The implementation uses Unity 2021.3.27f1, C#, Azure SpeechRecognizer, and a segmentation silence timeout of 0.3 s. Evaluation includes an exploratory study with 29 participants and a within-subjects user study with 10 graduate students comparing Transcript, Word Cloud, and VIVRA. Reported means include enjoyment of visualizing ideas—VIVRA $S$8, Word Cloud $S$9, Transcript $w$0—and reflection scores such as tracking ideas $w$1 and reflecting on ideas $w$2. A repeated-measures one-way ANOVA finds a significant main effect on reflection activities, with $w$3. The limitations are also explicit: too many balloons can overwhelm users, LLM topic extraction can create irrelevant balloons, some users may feel self-conscious speaking aloud, validation was limited to short sessions, and better semantic grouping is a future direction (Xing et al., 2024).

Taken together, these adjacent systems indicate that the broader MindVoyager motif extends beyond text-only generation or evaluation. A plausible implication is that exploration becomes a general systems principle: DPP-based exploration of semantic output space in synthetic data generation, mediator-controlled exploration of hidden cognition in therapist evaluation, screenshot-guided exploration of spatial environments in Minecraft, and immersive exploration of personal thought structure in VR.