Related papers: The A-R Behavioral Space: Execution-Level Profilin…

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where…

The development of believable, natural, and interactive digital artificial agents is a field of growing interest. Theoretical uncertainties and technical barriers present considerable challenges to the field, particularly with regards to…

Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability question remains under-explored: does the same agent behave the same way twice? We present a…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

We propose a suite of tasks to evaluate the instrumental self-reasoning ability of large language model (LLM) agents. Instrumental self-reasoning ability could improve adaptability and enable self-modification, but it could also pose…

Existing tasks fall short in evaluating reasoning ability of Large Language Models (LLMs) in an interactive, unknown environment. This deficiency leads to the isolated assessment of deductive, inductive, and abductive reasoning, neglecting…

Human decision-making belongs to the foundation of our society and civilization, but we are on the verge of a future where much of it will be delegated to artificial intelligence. The arrival of Large Language Models (LLMs) has transformed…

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during…

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In this work, we argue that this gap persists even under…

Large Language Models' safety-aligned behaviors, such as refusing harmful queries, can be represented by linear directions in activation space. Previous research modeled safety behavior with a single direction, limiting mechanistic…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Large Language Models (LLMs) show promise as data analysis agents, but existing benchmarks overlook the iterative nature of the field, where experts' decisions evolve with deeper insights of the dataset. To address this, we introduce…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Large Language models (LLMs) have shown remarkable success in assisting robot learning tasks, i.e., complex household planning. However, the performance of pretrained LLMs heavily relies on domain-specific templated text data, which may be…

This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models (LLMs) interact with each other. Most current governance practices still rely on single-agent safety…

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning,…

Behavioral parameters such as loss aversion, herding, and extrapolation are central to asset pricing models but remain difficult to measure reliably. We develop a framework that treats large language models (LLMs) as calibrated measurement…