9 papers
Decay-Ramsey Sequences
Francesco Di Braccio, Simon Griffiths, Pedram Noohi +1
Given a sequence of positive real numbers, we say that a colouring is -bounded if the proportion of edges coloured…
Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications
Peng Qi, Chunliang Lyu, Gang Li +4
AI agents based on foundation models (FMs) have demonstrated strong capabilities to perform complex open-ended tasks. However, they face some common challenges in practice: (a) age…
PADMÉ: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators
Cheng Chang, Yining Mao, Peng Qi
Language models are frequently employed to evaluate other language models. An LM evaluator scoring agentic behaviors across multiple criteria is valuable, provided that its decisio…
REC-RL: Referring expression counting via Gaussian and range-based reward optimization
Hui Liu, Yunlai Teng, Kunlong Bai +4
Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual un…
When Vision Speaks for Sound
Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu +6
Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate…
OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
Boyu Zhu, Xiaofei Wen, Wenjie Jacky Mo +4
Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardr…
WARC-Bench: Web Archive Based Benchmark for GUI Subtask Executions
Sanjari Srivastava, Gang Li, Cheng Chang +8
Training web agents to navigate complex, real-world websites requires them to master - short-horizon interactions on multiple UI components (e.g., choosing the…
Learning Efficient Guardrails for Compliance
Xiaofei Wen, Wenjie Jacky Mo, Yanan Xie +2
Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard saf…
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
Yu Gu, Kai Zhang, Yuting Ning +9
Language agents based on large language models (LLMs) have demonstrated great promise in automating web-based tasks. Recent work has shown that incorporating advanced planning algo…