Traces

Follow this topic Ask about this topic

Momentum

47 papers in the last four weeks, up 262% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 257

All topics

Learning Lifted Action Models from Unsupervised Visual Traces
Apr 21, 2026Kai Xi, Stephen Gould, Sylvie ThiébauxAction Prediction Action Expert
School of Computing, The Australian National University · LAAS-CNRS, Universit´e de Toulouse
Where Fake Citations Are Made: Tracing Field-Level Hallucination to Specific Neurons in LLMs
Apr 20, 2026Yuefei Chen, Yihao Quan, Xiaodong Lin +1Citation Hallucination Visual Hallucinations
Rutgers University
Symbolic Synthesis for LTLf+ Obligations
Apr 20, 2026Giuseppe De Giacomo, Christian Hagemeier, Daniel Hausmann +1Linear Temporal Logics Invariant Synthesis
University of Oxford, UK · University of Liverpool, UK · University of Gothenburg and Chalmers University of Technology, Sweden
Causal-Temporal Event Graphs: A Formal Model for Recursive Agent Execution Traces
Apr 19, 2026Simon FoldvikTraces Runtime Enforcement
Independent researcher
A Multi-Agent Approach for Claim Verification from Tabular Data Documents
Apr 19, 2026Rudra Ranajee Saha, Laks V. S. Lakshmanan, Raymond T. NgAgent Loop Multi-Agent Communication
University of British Columbia
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Apr 15, 2026Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2Fact-Checking Category-Aware Atomic Claims
MBZUAI, UAE · TU Darmstadt, Germany · IIT Delhi, India
What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features
Apr 6, 2026Dayeon Ki, Kevin Duh, Marine CarpuatMultilingual Benchmark Reasoning Traces
University of Maryland · Johns Hopkins University
APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
Mar 31, 2026Pratyay Banerjee, Masud Moshtaghi, Ankit ChadhaPeak Memory Autonomous Agents
Amazon, AGI / Sunnyvale, USA
TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
Mar 22, 2026Feng Liu, Xin Cui, Jian Xu +11Full Waveform Inversion Traces
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China. · Shanghai Artificial Intelligence Laboratory, Shanghai, China. · School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China. +3
Can We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in the LLM Era
Mar 20, 2026Nabelanita Utami, Ryohei SasanoAi-Assisted Writing Traces
Graduate School of Informatics, Nagoya University
Learning to Evict from Key-Value Cache
Feb 10, 2026Luca Moschella, Laura Manduchi, Ozan SenerKey-Value Cache Eviction Key-Value Cache
Apple
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
Jan 29, 2026Shicheng Fan, Kun Zhang, Lu ChengCausal Representation Learning Single Trajectory
University of Illinois at Chicago · Carnegie Mellon University · Mohamed bin Zayed University of Artificial Intelligence
Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature
Jan 12, 2026Julian Schelb, Michael Wittweiler, Marie Revellio +2Multilingual Benchmark Analogy
Department of Computer and Information Science, University of Konstanz · Institute of Archaology, Classical Philology and Ancient Studies, University of Zurich · Department of Latin Philology, University of Konstanz
Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster
Nov 4, 2025Shin Kamada, Takumi IchimuraLandslides Road Networks
S. Kamada is with Hiroshima City University, Hiroshima, Japan · T. Ichimura is with Prefectural University of Hiroshima, Hiroshima, Japan
When Users Are Happy but Agents Are Wrong: Multi-Dimensional Evaluation of Tool-Augmented Dialogue
Oct 22, 2025Tanya Shourya, Yingfan Wang, Zhaoyi Joey Hou +3Dialogue Benchmarks Conversational Artificial Intelligence
AWS AI Labs · University of Pittsburgh
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Sep 28, 2025Kaisen Yang, Tinghe Zhang, Rushi Shah +4Large Language Model Planning Stochastic Exploration
1Qizhi Institute · 2Dept. of Computer Science, Tsinghua University · College of AI, Tsinghua University +4
Tracing Computation Density in LLMs
Date pendingCorentin Kervadec, Iuliia Lysova, Iuri Macocco +2Transformer Architectures Traces
Universitat Pompeu Fabra · ICREA

Apr 21, 2026, cs.AIJ/K move · Enter open · S save

Learning Lifted Action Models from Unsupervised Visual Traces

Kai Xi, Stephen Gould, Sylvie Thiébaux

School of Computing, The Australian National University · LAAS-CNRS, Universit´e de Toulouse

Action Prediction Action Expert Classical Planning Deep Learning Traces

Open paper AskPDF arXiv

Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a more challenging setting: learning lifted action models from sequences of state images, without action observation. We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model. We also introduce a mixed-integer linear program (MILP) to prevent prediction collapse and self-reinforcing errors among predictions. The MILP takes the predicted states, actions, and action model over a subset of traces and solves for logically consistent states, actions, and action model that are as close as possible to the original predictions. Pseudo-labels extracted from the MILP solution are then used to guide further training. Experiments across multiple domains show that integrating MILP-based correction helps the model escape local optima and converge toward globally consistent solutions.

Momentum

Related topics

Latest papers 257