paper-with-me

홈 › Papers

MARPLE: A Benchmark for Long-Horizon Inference

2024-10-02 · Emily Jin, Zhuoyi Huang, Jan-Philipp Fränken, Weiyu Liu, Hannah Cha, Erik Brockbank, Sarah Wu, Ruohan Zhang, Jiajun Wu, Tobias Gerstenberg

Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including visual, language, and auditory cues. We introduce MARPLE, a benchmark for evaluating long-horizon inference capabilities using multi-modal evidence. Our benchmark features agents interacting with simulated households, supporting vision, language, and auditory stimuli, as well as procedurally generated environments and agent behaviors. Inspired by classic ``whodunit'' stories, we ask AI models and human participants to infer which agent caused a change in the environment based on a step-by-step replay of what actually happened. The goal is to correctly identify the culprit as early as possible. Our findings show that human participants outperform both traditional Monte Carlo simulation methods and an LLM baseline (GPT-4) on this task. Compared to humans, traditional inference models are less robust and performant, while GPT-4 has difficulty comprehending environmental changes. We analyze what factors influence inference performance and ablate different modes of evidence, finding that all modes are valuable for performance. Overall, our experiments demonstrate that the long-horizon, multimodal inference tasks in our benchmark present a challenge to current models.

📄 PDF Abstract BibTeX arXiv:2410.01926

Code (1)

marple-benchmark/marple 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

MissMarple : A Novel Socio-inspired Feature-transfer Learning Deep Network for Image Splicing Detection

2021-12-15 · Angelina L. Gokhale, Dhanya Pramod, Sudeep D. Thepade, Ravi Kulkarni

In this paper we propose a novel socio-inspired convolutional neural network (CNN) deep learning model for image splicing detection. Based on the premise that learning from the detection of coarsely spliced image regions…

Deep LearningTransfer Learning

Mobile Manipulation with Active Inference for Long-Horizon Rearrangement Tasks

2025-07-23 · Corrado Pezzato, Ozan Çatal, Toon Van de Maele, Riddhi J. Pitliya 외 arxiv

Despite growing interest in active inference for robotic control, its application to complex, long-horizon tasks remains untested. We address this gap by introducing a fully hierarchical active inference architecture for…

LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making

2026-07-10 · Yanzhen Chen, Zihan Xu, Xiaocheng Zhang, Zhiting Fan 외 arxiv

In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and to…

Information Retrieval

h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning

2025-10-08 · Sumeet Ramesh Motwani, Alesia Ivanova, Ziyang Cai, Philip Torr 외 arxiv

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level superv…

Reinforcement Learning

Koopman Autoencoders with Continuous-Time Latent Dynamics for Fluid Dynamics Forecasting

2026-02-02 · Rares Grozavescu, Pengyu Zhang, Etienne Meunier, Mark Girolami arxiv

Forecasting physical systems over long horizons from irregularly sampled observations demands models that are stable, computationally efficient, and free of fixed-timestep assumptions. We address this with a continuous-t…