arXiv subjects

Thomas L. Griffiths

Publications and source records attributed to Thomas L. Griffiths.

At least 37 records · Page 2Linked to original sources

arXiv2026

The Riddle Riddle: Testing Flexible Reasoning in Large Language Models and Humans

Humans flexibly adapt their reasoning strategies to the requirements of a given problem. Large language models (LLMs) have performed well on many cognitive tasks, however, it is unclear whether this accuracy is a result of pattern matching from training data or flexible reasoning. Here, we introduce a novel paradigm to test this question: the riddle riddle paradigm. Riddle riddles are word problems written to mimic popular riddles, but altered so their answers only require literal interpretations. Identifying correct answers requires looking past the structure of each question and flexibly apply different reasoning strategies based on the content. If LLMs respond to surface features, such as form, a riddle-like structure should cause models to use an inventive reasoning strategy even when a literal interpretation suffices. Alternatively, if LLMs reason based on content, they should flexibly switch strategies when appropriate. Across two experiments with nine state-of-the-art LLMs and 100 human participants, we show humans and LLMs fail on this paradigm in opposite directions. LLMs were far more accurate on genuine riddles than on riddle riddles (84.9% vs. 50.7%); whereas humans showed the reverse effect (50.5% vs. 80.5%). Error analysis shows that 90.8% of LLM errors on riddle riddles (the condition where they show diminished performance) were due to inappropriate use of inventive reasoning while only 57.6% of human errors on genuine riddles were due to overextending literal reasoning. Thus, while both groups make mistakes, reasoning mistakes are made more often by LLMs than by humans. Overall, LLMs' strong performance on genuine riddles may reflect memory retrieval rather than flexible strategy selection, and without stimuli designed to elicit this contrast, it becomes easy to conflate LLM-generated outputs that look like reasoning with genuine reasoning.

cs.CL↗

arXiv2026

Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist

Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-language-model agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science.

q-bio.NC↗

arXiv2026

Nothing from Something: Can a Language Model Discover 0?

AI systems based on artificial neural networks are being developed with aspirations of pushing the boundary of human mathematical knowledge. A key question for these systems is how much they can reach beyond their training data. Mathematical discovery requires a strong form of out of distribution generalization; the ability to hypothesize genuinely new - and potentially logically more powerful - mathematical structures. It has been hypothesized that language abilities support such generalizations in human cognition. In this work, we use simple arithmetic as a case study for examining how modern AI models could expand their mathematical horizons, evaluating whether these models can independently discover the concept of "zero". We show that (1) language models of a GPT-2 size are unable to perform this generalization at test time regardless of language pretraining, but (2) models can improve substantially after training on tens or hundreds of examples of zero. Additionally, we find that language pretraining reduces the number of required examples by approximately $50\%$, showing that language abilities can scaffold mathematical discovery in neural models.

cs.AI↗

arXiv2026

Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games

People make decisions differently in strategic interactions. Some update beliefs like a Bayesian; others exhibit biases like motivated reasoning. Although creators of large language models use simulated humans for safety evaluations and training, they often fail to cover this breadth of human behavior. We argue that cognitive science and economics provide a convenient tool for doing so, making use of mathematical models of human decision-making. We propose an approach that we call Equation-to-Behavior Prompting for guiding large language models to match cognitive models, and evaluate this approach on persuasion games based on legal decision-making. We find that large models can approximate equation-based specifications -- Bayesian updating, affine distortion, motivated updating, and Grether's $α$-$β$ model -- using prompting, but small models fail to do so. However, training small models with reinforcement learning to adhere to mathematical rules, Equation-to-Behavior RL, reduces belief error by 26.5% in out-of-distribution parameterizations. We show that these simulations can help create diverse training environments; training small models to consider different kinds of decision-makers improves average belief change by 2.5%--12% over Bayesian-only training, even when persuading GPT-5-mini. Our work could improve human simulations for training and evaluation in increasingly realistic settings, and could also enable novel research into more complicated mathematical models of human decision-making.

cs.AI↗

arXiv2026

RoboWits: Unexpected Challenges for Robotic Creative Problem Solving

The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments. However, current robotic benchmarks primarily emphasize skill-level execution and provide limited insight into such cognitive reasoning capabilities. We introduce RoboWits, a bi-manual robotic benchmark designed to systematically evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions. To enable scalable construction of high-quality reasoning-centric unexpected scenarios, we propose an automated task generation pipeline formulated as a multi-agent cooperative framework, comprising agents for seed task generation and verification, metric generation, scene generation, and task mutation. Using the pipeline, we curated 30 diverse seed tasks and 208 tasks with mutations and graded difficulty across geometry, material, and assembly-based reasoning. We benchmark popular robot policies, pre-trained VLAs, and oracle-state planners. Our results reveal a significant performance gap: while pre-trained VLAs exhibit preliminary success on seed tasks after single-task fine-tuning, they struggle to perform on mutated tasks, implying their brittleness in manipulation tasks requiring reasoning, strategy adaptation, and robustness to deceptive or constrained environments. Project page is available at https://umass-embodied-agi.github.io/RoboWits.

cs.RO↗

arXiv2026

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), to address these limitations: we use an LLM to generate diverse open-world scenarios as probabilistic programs, run probabilistic inference to produce distributional target responses to queries, and then fine-tune on these probabilistic soft labels. Using this approach, we fine-tune LLMs on 10,000 programmatically generated scenarios and evaluate on held-out motifs, human-labeled judgments, and external benchmarks. Overall, PPT substantially improves estimation accuracy on held-out inductive tasks, increases alignment with human judgments, and transfers to external benchmarks for estimation and calibration. Additionally, the gains in raw calibration are not subsumed by post-hoc temperature scaling, showing that the models have more deeply internalized uncertainty compared to output rescaling. Together, these results suggest that probabilistic-program-mediated fine-tuning is a promising approach for post-training LLMs to reliably perform approximate inductive inference.

cs.CL↗

arXiv2026

Post-training makes large language models less human-like

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

cs.CL↗

arXiv2026

Investigating Concept Alignment Using Implausible Category Members

Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probing concept understanding, asking questions about plausible category members (e.g., "Is a car a vehicle?") is likely to recall patterns in the model's vast training data. We pursue an alternative strategy, characterizing the boundaries of conceptual categories by asking about implausible category members (e.g., "Is an olive a vehicle?") to probe the kind of concept-level knowledge we take for granted in fellow humans. We characterize concept boundaries for a set of fundamental concepts by studying AI systems' assignments of objects to superordinate categories from a classic psychological study by Rosch and Mervis, as well as their assignments of the same objects to mismatched superordinate categories. We compare these assignments to those made by human participants on the full range of within-category and cross-category assignment tasks. Our results reveal a range of concepts for which which models differ in meaningful and surprising ways from humans, including treating "words" as belonging to categories like "vehicles" and "clothing," identifying several "vegetable" category members as "fruit," and assigning exemplars from non-weapon categories to the "weapons" category. We also demonstrate how these instances of concept misalignment translate into problematic downstream behavior with implications for AI safety.

cs.AI↗

arXiv2026

Evaluating Language Models' Evaluations of Games

Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over 100 novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.

cs.CL↗

arXiv2026

VideoGameBench: Can Vision-Language Models complete popular video games?

Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perform tasks that come naturally to humans--such as perception, spatial navigation, and memory management--remains understudied. Real video games are crafted to be intuitive for humans to learn and master by leveraging innate inductive biases, making them an ideal testbed for evaluating such capabilities in VLMs. To this end, we introduce VideoGameBench, a benchmark consisting of 10 popular video games from the 1990s that VLMs directly interact with in real-time. VideoGameBench challenges models to complete entire games with access to only raw visual inputs and a high-level description of objectives and controls, a significant departure from existing setups that rely on game-specific scaffolding and auxiliary information. We keep three of the games secret to encourage solutions that generalize to unseen environments. Our experiments show that frontier vision-language models struggle to progress beyond the beginning of each game. We find inference latency to be a major limitation of frontier models in the real-time setting; therefore, we introduce VideoGameBench Lite, a setting where the game pauses while waiting for the LM's next action. The best performing models, Gemini 2.5 Pro and Claude 3.7 Sonnet, complete only 0.48% of VideoGameBench and 1.6% of VideoGameBench Lite. We hope that the formalization of the human skills mentioned above into this benchmark motivates progress in these research directions.

cs.AI↗

arXiv2026

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, and wasted resources (measured in time, tokens, or file operations). We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems, where processors must operate under partial observability and communication constraints. In LATTE, a team of agents collaboratively construct and maintain a shared, evolving coordination graph which encodes sub-task dependencies, individual agent assignment, and the current state of sub-task progress. This protocol maintains consistency while empowering agents to dynamically allocate work, adapt coordination, and discover new tasks. Across multiple collaborative tasks and a variety of base models, we demonstrate how LATTE reduces token usage, wall-clock time, communication, and coordination failures (e.g. file conflicts and redundant outputs) while matching or exceeding the accuracy of standard designs including MetaGPT, decentralized teams, top-down Leader-Worker hierarchies, and static decompositions.

cs.MA↗

arXiv2026

Learning is Forgetting: LLM Training As Lossy Compression

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to learning in humans. We argue LLMs are best seen as an instance of lossy compression, where over training they learn by retaining only information in their training data relevant to their objective(s). We show pre-training results in models that are optimally compressed for next-sequence prediction, approaching the Information Bottleneck bound on compression. Across an array of open weights models, each compresses differently, likely due to differences in the data and training recipes used. However even across different families of LLMs the optimality of a model's compression, and the information present in it, can predict downstream performance on across a wide array of benchmarks, letting us directly link representational structure to actionable insights about model performance. In the general case the work presented here offers a unified Information-Theoretic framing for how these models learn that is deployable at scale.

cs.LG↗

arXiv2026

Do Large Language Models Mentalize When They Teach?

How do LLMs decide what to teach next: by reasoning about a learner's knowledge, or by using simpler rules of thumb? We test this in a controlled task previously used to study human teaching strategies. On each trial, a teacher LLM sees a hypothetical learner's trajectory through a reward-annotated directed graph and must reveal a single edge so the learner would choose a better path if they replanned. We run a range of LLMs as simulated teachers and fit their trial-by-trial choices with the same cognitive models used for humans: a Bayes-Optimal teacher that infers which transitions the learner is missing (inverse planning), weaker Bayesian variants, heuristic baselines (e.g., reward based), and non-mentalizing utility models. In a baseline experiment matched to the stimuli presented to human subjects, most LLMs perform well, show little change in strategy over trials, and their graph-by-graph performance is similar to that of humans. Model comparison (BIC) shows that Bayes-Optimal teaching best explains most models' choices. When given a scaffolding intervention, models follow auxiliary inference- or reward-focused prompts, but these scaffolds do not reliably improve later teaching on heuristic-incongruent test graphs and can sometimes reduce performance. Overall, cognitive model fits provide insight into LLM tutoring policies and show that prompt compliance does not guarantee better teaching decisions.

cs.AI↗

arXiv2026

Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in few shot learning - generalization across datasets can be limited, driving up training costs. As a consequence, other approaches such as in-context learning are typically used in this setting. To address this challenge, we introduce an efficient method for adapting the weights of LLMs to multiple distributions, Amortized Bayesian Meta-Learning for LoRA (ABMLL). This method builds on amortized Bayesian meta-learning for smaller models, adapting this approach to LLMs by reframing where local and global variables are defined in LoRA and using a new hyperparameter to balance reconstruction accuracy and the fidelity of task-specific parameters to the global ones. ABMLL supports effective generalization across datasets and scales to large models such as Llama3-8B and Qwen2-7B, outperforming existing methods on the CrossFit and Unified-QA datasets in terms of both accuracy and expected calibration error. We show that meta-learning can also be combined with in-context learning, resulting in further improvements in both these datasets and legal and chemistry applications.

cs.LG↗

arXiv2026

Levels of Analysis for Large Language Models

Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to the historical difficulties in understanding the human mind, we argue that methods developed in cognitive science can be useful for understanding large language models. We propose a framework for applying these methods based on the levels of analysis that David Marr proposed for studying information processing systems. By revisiting established cognitive science techniques relevant to each level and illustrating their potential to yield insights into the behavior and internal organization of large language models, we aim to provide a toolkit for making sense of these new kinds of minds.

cs.CL↗

arXiv2026

An evolutionary perspective on modes of learning in Transformers

The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via in-weight learning (IWL), and the ephemeral modulation of inferences via in-context learning (ICL), which leverages contextual information maintained in the model's activations. Evolutionary biology tells us that the predictability of the environment across timescales predicts the extent to which analogous strategies should be preferred. Genetic evolution adapts to stable environmental features by gradually modifying the genotype over generations. Conversely, environmental volatility favors plasticity, which enables a single genotype to express different traits within a lifetime, provided there are reliable cues to guide the adaptation. We operationalize these dimensions (environmental stability and cue reliability) in controlled task settings (sinusoid regression and Omniglot classification) to characterize their influence on learning in Transformers. We find that stable environments favor IWL, often exhibiting a sharp transition when conditions are static. Conversely, reliable cues favor ICL, particularly when the environment is volatile. Furthermore, an analysis of learning dynamics reveals task-dependent transitions between strategies (ICL to IWL and vice versa). We demonstrate that these transitions are governed by (1) the asymptotic optimality of the strategy with respect to the environment, and (2) the optimization cost of acquiring that strategy, which depends on the task structure and the learner's inductive bias.

cs.LG↗

arXiv2026

Language Model Teams as Distributed Systems

Large language models (LLMs) are growing increasingly capable, prompting recent interest in LLM teams. Yet, despite increased deployment of LLM teams at scale, we lack a principled framework for addressing key questions such as when a team is helpful, how many agents to use, how structure impacts performance -- and whether a team is better than a single agent. Rather than designing and testing these possibilities through trial-and-error, we propose using distributed systems as a principled foundation for creating and evaluating LLM teams. We find that many of the fundamental advantages and challenges studied in distributed computing also arise in LLM teams, highlighting the rich practical insights that can come from the cross-talk of these two fields of study.

cs.MA↗

arXiv2026

Why Human Guidance Matters in Collaborative Vibe Coding

Writing code has been one of the most transformative ways for human societies to translate abstract ideas into tangible technologies. Modern AI is changing this process by enabling experts and non-experts alike to generate code without actually writing it, instead using natural language instructions or "vibe coding". While increasingly popular, the impact of vibe coding on productivity and collaboration, and the role of humans in this process, remains unclear. Here, we introduce a controlled experimental framework for studying collaborative vibe coding and use it to compare human-led, AI-led, and hybrid groups. Across 20 experiments involving 737 human participants, we show that people provide uniquely effective high-level instructions for vibe coding, whereas AI-provided instructions often result in performance collapse. We further demonstrate that hybrid systems perform best when humans lead by providing instructions while evaluation is delegated to AI. Although AI systems can rapidly optimize performance for specific tasks, our work highlights the importance of human guidance in shaping future hybrid societies.

cs.HC↗