Related papers: Authority-Level Priors: An Under-Specified Constra…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

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…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

We investigate how peer pressure influences the opinions of Large Language Model (LLM) agents across a spectrum of cognitive commitments by embedding them in social networks where they update opinions based on peer perspectives. Our…

AI systems are increasingly deployed in high-stakes contexts (medical diagnosis, legal research, financial analysis) under the assumption they can be governed by norms. This paper demonstrates that the assumption is formally invalid for…

Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…

In high-complexity abstract reasoning, a system must infer a latent rule from a few examples or structured observations and apply it to unseen instances. LLMs can express such rules as programs, but ordinary conversation-based refinement is…

Modeling latent clinical constructs from unconstrained clinical interactions is a unique challenge in affective computing. We present ADAPTS (Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms), a framework for…

This paper presents a logic programming-based framework for policy-aware autonomous agents that can reason about potential penalties for non-compliance and act accordingly. While prior work has primarily focused on ensuring compliance, our…

Autonomous agentic systems are increasingly deployed in regulated, high-stakes domains where decisions may be irreversible and institutionally constrained. Existing safety approaches emphasize alignment, interpretability, or action-level…

LLMs enable qualitative coding at large scale, but assessing reliability remains challenging where human experts seldom agree. We investigate confidence-diversity calibration as a quality assessment framework for accessible coding tasks…

When a system commits to a hypothesis, much of the evidential structure behind that commitment is lost to compression. Standard accounts assume that selected content and scalar confidence suffice for downstream control. This paper argues…

Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their…

As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world interaction, their long-term reliability becomes a critical concern. We identify the Alignment…

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation, yet existing research has mostly evaluated their adherence to…

Answer-set programming (ASP) is a successful problem-solving approach in logic-based AI. In ASP, problems are represented as declarative logic programs, and solutions are identified through their answer sets. Equilibrium logic (EL) is a…

Machine learning can provide predictions with disparate outcomes, in which subgroups of the population (e.g., defined by age, gender, or other sensitive attributes) are systematically disadvantaged. In order to comply with upcoming…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…