相关论文: Identity as Attractor: Geometric Evidence for Pers…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Language is not only a tool for communication but also a medium for human cognition and reasoning. If, as linguistic relativity suggests, the structure of language shapes cognitive patterns, then large language models (LLMs) trained on…

Previous work has showcased the intriguing capabilities of Large Language Models (LLMs) in instruction-following and rhetorical fluency. However, systematic exploration of their dual capabilities to autonomously persuade and resist…

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…

Large Language Models (LLMs) excel at in-context learning, the ability to use information provided as context to improve prediction of future tokens. Induction heads have been argued to play a crucial role for in-context learning in…

Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models…

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems,…

This research explores the potential of Large Language Models (LLMs) to utilize psychometric values, specifically personality information, within the context of video game character development. Affective Computing (AC) systems quantify a…

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory…

Identifying the strategic uses of reformulation in discourse remains a key challenge for computational argumentation. While LLMs can detect surface-level similarity, they often fail to capture the pragmatic functions of rephrasing, such as…

Modern AI agents suffer from a fundamental identity problem: when context windows overflow and conversation histories are summarized, agents experience catastrophic forgetting -- losing not just information, but continuity of self. This…

We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations from 1,200 persona-conditioned agents and two no-persona settings, we analyze captions,…

The proficiency of Large Language Models (LLMs) in coding tasks is often a reflection of their extensive pre-training corpora, which typically collapses when confronted with previously unfamiliar programming languages. Departing from…

Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstructured embedding…

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

This paper presents a psychologically-aware conversational agent designed to enhance both learning performance and emotional well-being in educational settings. The system combines Large Language Models (LLMs), a knowledge graph-enhanced…

We propose Curved Inference - a geometric Interpretability framework that tracks how the residual stream trajectory of a large language model bends in response to shifts in semantic concern. Across 20 matched prompts spanning emotional,…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynamic interaction…