Related papers: Rank-and-Reason: Multi-Agent Collaboration Acceler…

The development of Generalist Virtual Agents (GVAs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive…

We present $\textbf{Research Math Agents (RMA)}$, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition mathematics or formal theorem proving, RMA targets…

Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains a challenging engineering loop, driven not by training…

Protein Language Models (PLMs) such as ESM2 have been shown to be capable of zero-shot prediction of critical scalar properties of proteins (fitness). In this work, we show that injecting a dropout layer at inference time between a PLM's…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

Visual Language Models (VLMs) achieve promising results in medical reasoning but struggle with hallucinations, vague descriptions, inconsistent logic and poor localization. To address this, we propose a agent framework named Medical Visual…

Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as search-integrated reasoning. However, mainstream approaches…

We introduce V-Agent, a novel multi-agent platform designed for advanced video search and interactive user-system conversations. By fine-tuning a vision-language model (VLM) with a small video preference dataset and enhancing it with a…

We address the task of zero-shot video classification for extremely fine-grained actions (e.g., Windmill Dunk in basketball), where no video examples or temporal annotations are available for unseen classes. While image-language models…

Repository-level code agents have shown strong promise in real-world feature addition tasks, making reliable evaluation of their capabilities increasingly important. However, existing benchmarks primarily evaluate these agents as black…

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason about and prove code correctness remains in question. This paper offers a comprehensive study of…

Evaluating the quality of retrieval-augmented generation (RAG) and document reranking systems remains challenging due to the lack of scalable, user-centric, and multi-perspective evaluation tools. We introduce RankArena, a unified platform…

Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high Recall@k), often fail to identify the single best match (low Top-1 accuracy). This work investigates the use of zero-shot…

Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is…

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Visuomotor policies trained via imitation learning are capable of performing challenging manipulation tasks, but are often extremely brittle to lighting, visual distractors, and object locations. These vulnerabilities can depend…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…