Related papers: FM SO.P: A Progressive Task Mixture Framework with…
A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…
Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios,…
Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…
As Large Language Models (LLMs) evolve from passive text generators to active reasoning agents capable of interacting with external tools, the Model Context Protocol (MCP) has emerged as a key standardized framework for dynamic tool…
Various tasks, such as summarization, multi-hop question answering, or coreference resolution, are naturally phrased over collections of real-world documents. Such tasks present a unique set of challenges, revolving around the lack of…
Multi-agent systems represent a significant advancement in artificial intelligence, enabling complex problem-solving through coordinated specialized agents. However, these systems face fundamental challenges in context management,…
Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to…
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 advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Reinsurance decision-making exhibits the core structural properties that motivate multi-agent models: distributed and asymmetric information, partial observability, heterogeneous epistemic responsibilities, simulator-driven environment…
The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how agents conceptualize the environments within which they operate. Current paradigms are…
Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…
Software-intensive Systems-of-Systems (SoS) refer to an arrangement of managerially and operationally independent systems(i.e., constituent systems), which work collaboratively towards the achievement of global missions. Because some SoS…
Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference,…
Federated data processing (FDP) offers a promising approach for enabling collaborative analysis of sensitive data without centralizing raw datasets. However, real-world adoption remains limited due to the complexity of managing…
Spatial reasoning, the ability to ground language in 3D understanding, remains a persistent challenge for Vision-Language Models (VLMs). We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from…
AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…
Speech forensic tasks (SFTs), such as automatic speaker recognition (ASR), speech emotion recognition (SER), gender recognition (GR), and age estimation (AE), find use in different security and biometric applications. Previous works have…
The VAPO framework has demonstrated significant empirical success in enhancing the efficiency and reliability of reinforcement learning for long chain-of-thought (CoT) reasoning tasks with large language models (LLMs). By systematically…