Related papers: SPIN: Structural LLM Planning via Iterative Naviga…

Signal Temporal Logic (STL) is a powerful language for specifying temporally structured robotic tasks. Planning executable trajectories under STL constraints remains difficult when system dynamics and environment structure are not…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

It is evident that the current state of Large Language Models (LLMs) necessitates the incorporation of external tools. The lack of straightforward algebraic and logical reasoning is well documented and prompted researchers to develop…

While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation between these stages remain largely underexplored. Current…

Recently, self-play fine-tuning (SPIN) has been proposed to adapt large language models to downstream applications with scarce expert-annotated data, by iteratively generating synthetic responses from the model itself. However, SPIN is…

As modern HPC computing platforms become increasingly heterogeneous, it is challenging for programmers to fully leverage the computation power of massive parallelism offered by such heterogeneity. Consequently, task-based runtime systems…

Agentic tool use has gained traction with the rise of agentic tool calling, yet most existing work overlooks the complexity of multi-turn tool interactions. We introduce OrchDAG, a synthetic data generation pipeline that models tool…

LLM-augmented data systems enable semantic querying over structured and unstructured data, but executing queries with LLM-powered operators introduces a fundamental runtime-accuracy trade-off. In this paper, we present Stretto, a new…

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with…

The value of a systematic secondary study (a systematic mapping study (SMS) or a systematic literature review (SLR)) comes, directly, from its systematic nature. The formal, well-defined, objective and unbiased process guarantees that the…

In this paper, we present a novel framework that combines large language models (LLMs), digital twins and industrial automation system to enable intelligent planning and control of production processes. We retrofit the automation system for…

Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions…

This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs under expensive evaluations. Large language models (LLMs) are a promising assistant for…

Formulating mathematical models from real-world decision problems is a core task in Operational Research, yet it typically requires considerable human expertise and effort, limiting practical application. Recent advances in large language…

While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability in long-horizon domains. To bridge the gap between…

We introduce Reactive Action and Motion Planner (RAMP), which combines the strengths of sampling-based and reactive approaches for motion planning. In essence, RAMP is a hierarchical approach where a novel variant of a Model Predictive Path…

We consider the problem of evaluating regular spanners over compressed documents, i.e., we wish to solve evaluation tasks directly on the compressed data, without decompression. As compressed forms of the documents we use straight-line…

Planning for sequential robotics tasks often requires integrated symbolic and geometric reasoning. TAMP algorithms typically solve these problems by performing a tree search over high-level task sequences while checking for kinematic and…