The paper introduces DisCo, a framework that uses large language models (LLMs) to automatically generate interpretable symbolic cognitive models. DisCo employs evolutionary search guided by two structural components: a Validator that filters out structurally invalid models and a Cleaner that enhances parameter identifiability by removing redundancies. Experiments on three behavioral tasks show that DisCo produces models with performance comparable to task‑specific baselines, and ablation studies highlight the Validator’s role in maintaining psychologically meaningful structure.
arXiv:2610.02523v1 Announce Type: new Abstract: Developing cognitive models of algorithmic reasoning from behavioral data is a central problem in cognitive science that challenges current methods. Tr...
arXiv:2607. 12733v1 Announce Type: new Abstract: Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypotheses that explain observed behavior - remains poorly understood.
The paper presents a taxonomy of 28 cognitive elements derived from cognitive science to analyze reasoning in large language models (LLMs). Using a fine‑grained evaluation framework, the authors compare 192,000 model traces with 1,346 human think‑aloud traces, finding that while models deploy similar cognitive elements, they differ in usage patterns. The study introduces test‑time reasoning guidance that improves model accuracy on ill‑structured problems by 9.7 percentage points and highlights a research gap in self‑awareness, advocating for a shared vocabulary to diagnose failures and guide robust model development.
arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
Emergent Abilities in Large Language Models: A Survey reviews how scaling LLMs leads to previously unseen capabilities such as advanced reasoning, in-context learning, coding, and problem-solving. The paper critically examines definitions, inconsistencies, and the conditions that foster these abilities, including scaling laws, task complexity, pre‑training loss, quantization, and prompting strategies. It also discusses the extension to Large Reasoning Models and highlights safety concerns like deception, manipulation, and reward hacking, calling for improved evaluation and governance.
The paper investigates whether current reasoning models exhibit systematicity—the idea that understanding one concept should extend to closely related variations—by extending rule induction tasks from cognitive science. Using task isomorphisms like recombination and substitution, the authors generate structurally equivalent task variants and test models on them. Results show that while models can solve the original tasks, they frequently fail on these equivalent variants, indicating a lack of systematicity in their reasoning abilities.
arXiv:2606. 03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving?
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
arXiv:2609.34187v2 Announce Type: replace-cross Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...
The paper introduces the Mental World Model (MWM) and its implementation, the Multi-Branch Mental Evolution Architecture (MMEA), to explicitly construct subjective worlds and simulate continuous mental evolution influenced by historical experiences. MMEA outperforms leading large language models and Theory of Mind methods on DynToM and RecToM tasks, achieving 96.48% and 94.00% accuracy, and shows significant gains in mental state and behavior prediction, long‑sequence prediction, and implicit mental state inference. The authors argue that MWM offers an interpretable framework for continuous mental modeling, enabling AI to infer underlying mental states from linguistic data and to simulate dynamic cognitive processes, thereby laying groundwork for causal reasoning, personalized AI, sustained human‑AI interaction, and progress toward artificial general intelligence.
arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.