Related papers: What Do Agents Learn from Trajectory-SFT: Semantic…
Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…
While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…
Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online…
While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interruptions (TPI) from the primary user's ongoing flow, leaving them vulnerable to contextual…
Communication structure plays a key role in the learning capability of decentralized systems. Structural self-adaptation, by means of self-organization, changes the order as well as the input information of the agents' collective…
Advanced agentic intelligence is a prerequisite for deploying Large Language Models in practical, real-world applications. Diverse real-world APIs demand precise, robust function-calling intelligence, which needs agents to develop these…
The current mainstream approach to train natural language systems is to expose them to large amounts of text. This passive learning is problematic if we are interested in developing interactive machines, such as conversational agents. We…
We design a simple reinforcement learning (RL) agent that implements an optimistic version of $Q$-learning and establish through regret analysis that this agent can operate with some level of competence in any environment. While we leverage…
The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics…
General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…
This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturbations. By leveraging $U$-statistics for output-level…
Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments…
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented…
Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is…
Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation:…
LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model exploiting its own discoveries. We show that this assumption…
Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…
We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…
Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…
Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…