Related papers: From Raw Experience to Skill Consumption: A System…
General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…
Human problem-solving is enriched by a diversity of styles and personality traits, yet the development of Large Language Models (LLMs) has largely prioritized uniform performance benchmarks that favour specific behavioural tendencies such…
Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, high-quality skills are still largely written by hand. We introduce SkillGen, a…
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external…
While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this parametric knowledge is actually usable in performing downstream tasks. We propose a systematic…
Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for information retrieval, computation and external action. Existing studies remain fragmented across…
Circuit graph discovery has emerged as a fundamental approach to elucidating the skill mechanistic of language models. Despite the output faithfulness of circuit graphs, they suffer from atomic ablation, which causes the loss of causal…
It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
Constructing general knowledge by learning task-independent models of the world can help agents solve challenging problems. However, both constructing and evaluating such models remains an open challenge. The most common approaches to…
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…
Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…
Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate this issue, various modifications to a model's sampling…
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the…
Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines. However, LLMs are optimized for language generation instead of tool use during training or…
Although creativity is encouraged in the abstract it is often discouraged in educational and workplace settings. Using an agent-based model of cultural evolution, we investigated the idea that tempering the novelty-generating effects of…
Psycholinguistic research suggests that humans may build a representation of linguistic input that is 'good-enough' for the task at hand. This study examines what architectural features make language models learn human-like good-enough…
Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilities beyond what parametric memory alone supports. Existing methods assume external skills…
Conventional predictive modeling of parametric relationships in manufacturing processes is limited by the subjectivity of human expertise and intuition on the one hand and by the cost and time of experimental data generation on the other…
Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired…