Related papers: Learning to Compose for Cross-domain Agentic Workf…
Existing tools to detect text generated by a large language model (LLM) have met with certain success, but their performance can drop when dealing with texts in new domains. To tackle this issue, we train a ranking classifier called…
Quality-Diversity is a branch of stochastic optimization that is often applied to problems from the Reinforcement Learning and control domains in order to construct repertoires of well-performing policies/skills that exhibit diversity with…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
As LLM-based applications reach millions of customers, ensuring their scalability and continuous quality improvement is critical for success. However, the current workflows for developing, maintaining, and operating (DevOps) these…
The application of Large Language Models (LLMs) in healthcare is expanding rapidly, with one potential use case being the translation of formal medical reports into patient-legible equivalents. Currently, LLM outputs often need to be edited…
Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort. Context compression is also a challenging and pressing…
We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined. Instead, it emerges from an iterative process of search and optimization given certain…
Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating,…
We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across…
Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these…
Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such…
To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs…
We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and…
Building deployment-ready LLM agents requires complex orchestration of tools, data sources, and control flow logic, yet existing systems tightly couple agent logic to specific programming languages and deployment models. We present a…
Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the…
The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple…
The creation of high-quality datasets to improve Large Language Model (LLM) reasoning remains a significant challenge, as current methods often suffer from generating low-quality/incorrect answers and limited information richness from…
Iterative LLM systems(self-refinement, chain-of-thought, autonomous agents) are increasingly deployed, yet their temporal dynamics remain uncharacterized. Prior work evaluates task performance at convergence but ignores the trajectory: how…
The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…
Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications. However, their performance often degrades in context-specific scenarios, such as…