Related papers: Codified Context: Infrastructure for AI Agents in …
Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs…
Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…
Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent…
GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual…
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…
As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this challenge -- extracting reusable…
Agentic code assistants are a new generation of AI systems capable of performing end-to-end software engineering tasks. While these systems promise unprecedented productivity gains, their behavior and effectiveness depend heavily on…
Large Language Model (LLM)-based code analysis tools are adopted to automate software documentation tasks. However, the scalability of these approaches to real codebases, where Intermediate Representations (IR) exceed LLM context limits,…
Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting…
Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…
The rapid development of AI and LLMs has driven new methods of SDLC, in which a large portion of code, technical, and business documentation is generated automatically. However, since there is no single architectural framework that can…
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…
Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel…
LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…
Although large language models (LLMs) have advanced rapidly, robust automation of complex software workflows remains an open problem. In long-horizon settings, agents frequently suffer from cascading errors and environmental stochasticity;…
As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed…
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding…
We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge,…
AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where…