Related papers: Multi-Agent Verification: Scaling Test-Time Comput…

Multi-Agent Systems (MAS) are notoriously complex and hard to verify. In fact, it is not trivial to model a MAS, and even when a model is built, it is not always possible to verify, in a formal way, that it is actually behaving as we…

The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based…

Prevalent reinforcement learning~(RL) methods for fine-tuning LLM reasoners, such as GRPO or Leave-one-out PPO, abandon the learned value function in favor of empirically estimated returns. This hinders test-time compute scaling that relies…

As Large Language Models (LLMs) have become integral to both research and daily operations, rigorous evaluation is crucial. This assessment is important not only for individual tasks but also for understanding their societal impact and…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a persistent challenge. In this paper, we investigate…

Some multi-agent scenarios call for the possibility of evaluating specifications in a richer domain of truth values. Examples include runtime monitoring of a temporal property over a growing prefix of an infinite path, inconsistency…

Aligning large language models (LLMs) with human values is a central challenge for ensuring trustworthy and safe deployment. While existing methods such as Reinforcement Learning from Human Feedback (RLHF) and its variants have improved…

Multi-agent large language models (MA-LLMs) are a rapidly growing research area that leverages multiple interacting language agents to tackle complex tasks, outperforming single-agent large language models. This literature review…

Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a…

Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models (MLLMs) have significantly advanced the reasoning capabilities of such agents through…

The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks. However, a significant gap remains in assessing…

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a…

Large Language Models (LLMs) have revolutionized AI-generated content evaluation, with the LLM-as-a-Judge paradigm becoming increasingly popular. However, current single-LLM evaluation approaches face significant challenges, including…

Software Vulnerability (SV) assessment is a crucial process of determining different aspects of SVs (e.g., attack vectors and scope) for developers to effectively prioritize efforts in vulnerability mitigation. It presents a challenging and…

Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while…

Verification and Validation (V&V) is a series of activities, technical and managerial, which performed by system tester not the system developer in order to improve the system quality, system reliability and assure that product satisfies…

Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in tasks that require high precision due to their single-inference paradigm. While test-time scaling…

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without…

Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems across diverse domains. One effective paradigm for test-time scaling (TTS) involves LLM generators…