Related papers: PADME: Procedure Aware DynaMic Execution

Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language without engineering blueprints--leads to critical risks such as scope creep and open-loop failures.…

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…

Clinical practice guidelines are long, multimodal documents whose branching recommendations are difficult to convert into executable clinical decision support (CDS), and one-shot parsing often breaks cross-page continuity. Recent LLM/VLM…

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during…

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular…

The advent of Large Language Models (LLMs) has significantly transformed tasks across Software Engineering. In the context of Business Process Management, LLMs are now being explored as tools to derive process models directly from textual…

The emergence of LLMs has catalyzed a paradigm shift in autonomous agent development, enabling systems capable of reasoning, planning, and executing complex multi-step tasks. However, existing agent frameworks often suffer from…

Procedural Content Generation (PCG) offers scalable methods for algorithmically creating complex, customizable worlds. However, controlling these pipelines requires the precise configuration of opaque technical parameters. We propose a…

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing…

Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines. Unlike conventional programs, their execution, i.e., trajectories, is inherently stochastic and…

Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…

Scientific workflows in computational chemistry and materials science typically involve multiple interdependent steps, such as model preparation, system construction, simulation execution, and data analysis, that researchers have refined…

Agent systems based on large language models (LLMs) have shown great potential in complex reasoning tasks, but building efficient and generalizable workflows remains a major challenge. Most existing approaches rely on manually designed…

Autonomous agents in safety-critical applications must continuously adapt to dynamic conditions without compromising performance and reliability. This work introduces TAPA (Training-free Adaptation of Programmatic Agents), a novel framework…

When humans conceive how to perform a particular task, they do so hierarchically: splitting higher-level tasks into smaller sub-tasks. However, in the literature on natural language (NL) command of situated agents, most works have treated…

The enhancement of Visual Language Models (VLMs) has traditionally relied on knowledge distillation from larger, more capable models. This dependence creates a fundamental bottleneck for improving state-of-the-art systems, particularly when…

Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…

Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational strategies, implement them faithfully, and ensure that the resulting outcomes remain…

The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…

Coordinating navigation and manipulation with robust performance is essential for embodied AI in complex indoor environments. However, as tasks extend over long horizons, existing methods often struggle due to catastrophic forgetting,…