Related papers: ZORO: Active Rules for Reliable Vibe Coding
Can LLM agents explore codebases and reason about code semantics without executing the code? We study this capability, which we call agentic code reasoning, and introduce semi-formal reasoning: a structured prompting methodology that…
Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…
Vibe researching is an emerging paradigm in which human researchers provide high-level direction and critical judgment while LLM-based agents handle the labor-intensive execution of literature review, experimentation, data analysis, and…
Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically…
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations. However, behavioral cloning often suffers from the causal confusion problem where a policy relies on the noticeable…
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or…
Albrecht and Stone (2018) state that modeling of changing behaviors remains an open problem "due to the essentially unconstrained nature of what other agents may do". In this work we evaluate the adaptability of neural artificial agents…
App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle with long-horizon planning, failing to find the optimal…
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files…
Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to…
Artificial intelligence systems increasingly involve continual learning to enable flexibility in general situations that are not encountered during system training. Human interaction with autonomous systems is broadly studied, but research…
Generative AI is reshaping product design practices through "vibe coding," where product team members express intent in natural language and AI translates it into functional prototypes and code. Despite rapid adoption, little research has…
We present Coevo, an online platform that allows both humans and artificial agents to design shapes that solve different tasks. Our goal is to explore common shared design tools that can be used by humans and artificial agents in a context…
Personalization is the process of fitting a model to patient data, a critical step towards application of multi-physics computational models in clinical practice. Designing robust personalization algorithms is often a tedious,…
Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents…
Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they…
Cloud platforms run many software agents on each server node. These agents manage all aspects of node operation, and in some cases frequently collect data and make decisions. Unfortunately, their behavior is typically based on pre-defined…
Emotions have a major interactive role in defining how humans interact with their environment by encoding their perception to external events and accordingly, influencing their cognition and decision-making process. Therefore, increasing…
Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols…
Natural head rotation is critical for believable embodied virtual agents, yet this micro-level behavior remains largely underexplored. While head-rotation prediction algorithms could, in principle, reproduce this behavior, they typically…