Related papers: Codified Context: Infrastructure for AI Agents in …
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…
AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark…
Building and evaluating enterprise AI systems requires synthetic organizational corpora that are internally consistent, temporally structured, and cross-artifact traceable. Existing corpora either carry legal constraints or inherit…
The rapid emergence of multi-agent AI systems (MAS), including LangChain, CrewAI, and AutoGen, has shaped how large language model (LLM) applications are developed and orchestrated. However, little is known about how these systems evolve…
A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques,…
Achieving expert-level performance in simulation-based training relies on the creation of complex, adaptable scenarios, a traditionally laborious and resource intensive process. Although prior research explored scenario generation for…
Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a…
Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions…
Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent behavior. We propose…
LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incurs both monetary cost and attention dilution. To understand…
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…
Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conversation bounded, but summarization is inherently lossy and…
Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…
Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…
Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…
A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…
The rapid development of mobile GUI agents has stimulated growing research interest in long-horizon task automation. However, building agents for these tasks faces a critical bottleneck: the reliance on ever-expanding interaction history…
Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent advances in large language model (LLM)-based multi-agent…
The engineering design process often demands expertise from multiple domains, leading to complex collaborations and iterative refinements. Traditional methods can be resource-intensive and prone to inefficiencies. To address this, we…
Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…