Lunch at ICAPS 2026
Lunch is provided to all participants from June 28th to July 2nd (inclusive). On June 27th, lunch is provided to DC & Launchpad participants (students, mentors, organizers) and to the Council participants.
  • June 27th, 28th, 29th: Chef's Selection of Sandwiches, Soup, Tea & Coffee
  • June 30th, July 1st, 2nd: Buffet Lunch (1 Main Course & 1 Vegan Main Course) served with Seasonal Vegetables, Rice & Potatoes, and Tea & Coffee

Sunday, June 28, 2026 — Workshops & Tutorials Day 1 ↑ Back to Navigation

09:00 – 12:30 — Morning Sessions (Coffee Break 10:30 – 10:50 in the open space and meeting rooms on the second floor)
GenPlan
Generalization in Planning — Full Day — Room 6
HAXP
Human-Aware and Explainable Planning — Full Day — Room 3
KEPS
Knowledge Engineering for Planning and Scheduling — Full Day — Room 9
PRL
Bridging the Gap Between AI Planning and (Reinforcement) Learning — Full Day — Room 1+2
Tutorial 1: Language2Plan
Language-to-Plan — Room 5
Tutorial 2: Deepxube
A Hands-on Deepxube Tutorial — Room 7
13:00 – 14:30 — — Sussex Restaurant
14:30 – 18:00 — Afternoon Sessions (Coffee Break 16:00 – 16:20 in the open space and meeting rooms on the second floor)
GenPlan
Generalization in Planning — Full Day — Room 6
HAXP
Human-Aware and Explainable Planning — Full Day — Room 3
KEPS
Knowledge Engineering for Planning and Scheduling — Full Day — Room 9
PRL
Bridging the Gap Between AI Planning and (Reinforcement) Learning — Full Day — Room 1+2
RPG
Roles of Planning in Games — Room 5
PR-BGI
Planning and Reasoning about Beliefs, Goals and Intentions — Room 7

Monday, June 29, 2026 — Workshops & Tutorials Day 2 ↑ Back to Navigation

09:00 – 12:30 — Morning Sessions (Coffee Break 10:30 – 10:50 in the open space and meeting rooms on the second floor)
LM4Plan
Planning in the Era of Large Language Models — Full Day — Room 1+2
PlanRob
Planning and Robotics — Full Day — Room 9
HSDIP
Heuristics and Search for Domain-independent Planning — Full Day — Room 7
RIPL
Reliability in Planning and Learning — Full Day — Room 6
Tutorial 3: Planning Ontology
Planning Ontology — Room 5
12:30 – 14:00 — — Sussex Restaurant
14:00 – 17:30 — Afternoon Sessions (Coffee Break 15:30 – 15:50 in the open space and meeting rooms on the second floor)
LM4Plan
Planning in the Era of Large Language Models — Full Day — Room 1+2
PlanRob
Planning and Robotics — Full Day — Room 9
HSDIP
Heuristics and Search for Domain-independent Planning — Full Day — Room 7
RIPL
Reliability in Planning and Learning — Full Day — Room 6
CASP:ER
Constraint and Satisfiability-based Planning — Room 3
HPlan
Hierarchical Planning — Room 5
Opening Reception (17:30 – 19:30) — Fitzwilliam Suites & Pre-Function Area

Tuesday, June 30, 2026 — Main Conference Day 1 ↑ Back to Navigation

08:45 – 09:00 — Opening Remarks — Plenary Room - Pembroke & Herbert
09:00 – 10:00 — Invited Talk: Nick Hawes — Plenary Room - Pembroke & Herbert
10:00 – 10:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
10:30 – 12:00 — Morning Sessions
Session 1A: Classical Planning I
Plenary Room - Pembroke & Herbert — Chair: Gabriele Röger
10:30   Simplifying Planning Tasks with Fact-Level Relevance Analysis
Cameron Allen, Anita de Mello Koch, Harsha Kokel, George Konidaris and Michael Katz
10:45   Monotonic Variants of Saturated Cost Partitioning
Mauricio Salerno, Raquel Fuentetaja and Jendrik Seipp
10:55   Potential Heuristics as Real-Valued Multilinear Polynomials Best Paper Runner-Up
Augusto B. Corrêa, Simon Dold and Malte Helmert
11:05   Planner Museum: Evaluating Classical Planners Over Time
Arnaud Lequen, Oliver Joergensen, Windy Phung, Elliot Gestrin, Damien Van Meerbeeck, Markus Fritzsche, Dominik Drexler and Jendrik Seipp
Session 1B: Applications I
Breakout Room - Lansdowne — Chair: Jane Jean Kiam
10:30   GPMS: A Generalized Parallel Machine Scheduling Framework with Rich Temporal and Resource Constraints Best Student Paper Runner-Up
Lukas Frühwirth, Christoph Einspieler, Nysret Musliu and Felix Winter
10:45   Worksworld: A Domain for Integrated Numeric Planning and Scheduling of Distributed Pipelined Workflows
Taylor Paul and William Regli
11:00   Learning-Based Peak Temperature Optimization for Hard Real-Time Pipeline Schedules
Qiangxiao Zhou, Yiheng Wang, Hangbin Xu and Long Cheng
11:15   Beyond Pruning: Leveraging Dominance Relations for Heuristic Propagation
María Fernanda Salerno Garmendia, Daniel Fišer and Álvaro Torralba
11:30   Finding a Dominating State in a Haystack: Efficient Data Structures for Dominance Pruning
María Fernanda Salerno Garmendia, Daniel Fišer and Álvaro Torralba
11:45   Planning with Minimal Disruption
Alberto Pozanco, Marianela Morales, Daniel Borrajo and Manuela Veloso
11:15   Planning under Observation Mismatch for Traffic Signal Control via Adaptive Modular World Models
Zherui Huang, Yicheng Liu, Chumeng Liang and Guanjie Zheng
11:30   Near-Future Traffic Forecasting for Planning-based Traffic Signal Optimisation
Mattia Chiari, Francesco Percassi, Alfonso Emilio Gerevini and Mauro Vallati
11:45   Deep RL for Fast Long-Horizon Operations Scheduling on NASA's Carruthers Geocorona Observatory Mission
Alex Zhang, Jackson Craig and Lara Waldrop
12:00 – 13:30 — — Sussex Restaurant
13:30 – 15:00 — Afternoon Sessions
Session 2A: Model Learning and Model Repair
Plenary Room - Pembroke & Herbert — Chair: Roman Barták
13:30   Domain Model Acquisition From Binary Traces
Arash Haratian, Arnaud Lequen, Daniel Gnad and Jendrik Seipp
13:45   Learning Numeric Action Models with Anytime Guarantees
Diego Aineto and Enrico Scala
14:00   Learning Lifted Action Models from Unsupervised Visual Traces Best Paper
Kai Xi, Stephen Gould and Sylvie Thiebaux
14:20   On Sample-Efficient Generalized Planning via Learned Transition Models
Nitin Gupta, Vishal Pallagani, John A. Aydin and Biplav Srivastava
Session 2B: Multi-Agent Planning
Breakout Room - Lansdowne — Chair: Ariel Felner
13:30   Risk-Bounded Multi-Agent Visual Navigation via Iterative Risk Allocation
Viraj Parimi and Brian Williams
13:45   Online Learning for Decentralized Multi-Agent Planning in Repeated Hedonic Skill Games
Jaber Valizadeh and Ray Telikani
14:00   Towards a Unified View of Social Laws with Instantaneous Actions
Alexander Tuisov, Evgeny Mishlyakov, Alexander Shleyfman and Erez Karpas
14:10   Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning
Nhat Nguyen, Duong Nguyen, Gianluca Rizzo and Hung Nguyen
14:20   Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning
Emanuele Musumeci, Michele Brienza, Francesco Argenziano, Abdel Hakim Drid, Vincenzo Suriani, Daniele Nardi, and Domenico D. Bloisi
14:30   A Constraint Formulation for Domain Repair with Ground or Lifted Test Plans
Nika Beriachvili and Arthur Bit-Monnot
14:45   Automated Planning Instance Generation with Neuro-Symbolic AI
Carlos Núñez-Molina, Pablo Mesejo and Juan Fernández-Olivares
14:30   Optimal Solutions for the Moving Target Vehicle Routing Problem via Branch-and-Price with Relaxed Continuity
Anoop Bhat, Geordan Gutow, Zhongqiang Ren, Sivakumar Rathinam and Howie Choset
14:45   Optimal Path Planning in Hostile Environments
Andrzej Kaczmarczyk, Šimon Schierreich, Nicholas Axel Tanujaya and Haifeng Xu
15:00 – 15:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
15:30 – 17:00 — Afternoon Sessions
Session 3A: Planning under Uncertainty and Non-Determinism (FOND, POMDPs, Abstractions)
Plenary Room - Pembroke & Herbert — Chair: Sylvie Thiébaux
15:30   Leveraging the Value of Information in POMDP Planning
Zakariya Laouar, Qi Heng Ho and Zachary Sunberg
15:45   Memory Assignment for Finite-Memory Strategies in Adversarial Patrolling Games
Vojtěch Kůr, Vít Musil and Vojtěch Řehák
16:00   Planning under Distribution Shifts with Causal POMDPs
Matteo Ceriscioli and Karthika Mohan
16:10   Algorithms for Deciding the Safety of States in Fully Observable Non-deterministic Problems
Johannes Schmalz and Chaahat Jain
16:20   Constrained and Robust Policy Synthesis with Satisfiability-Modulo-Probabilistic-Model-Checking
Linus Heck, Filip Macák, Milan Češka and Sebastian Junges
Session 3B: Routing and Scheduling
Breakout Room - Lansdowne — Chair: J. Christopher Beck
15:30   Scalable Algorithms with Provable Optimality Bounds for the Multiple Watchman Route Problem
Srikar Gouru, Ariel Felner and Jiaoyang Li
15:45   H-ANTS: Hierarchical Ant System with Insert-and-Prune Charging for Capacitated Electric Vehicle Routing
Chuyin Peng, Feng-Feng Wei and Wei-Neng Chen
16:00   EMOA*: A Framework for Search-Based Multi-Objective Path Planning
Zhongqiang Ren, Carlos Hernández, Maxim Likhachev, Ariel Felner, Sven Koenig, Oren Salzman, Sivakumar Rathinam and Howie Choset
16:15   Learning-Guided Simulated Annealing for the Capacitated Vehicle Routing Problem
Jules Andretti, Jérémie Cabessa and Yann Strozecki
16:30   Complete and Optimal Robust Planning against Nature
Lukas Chrpa and Erez Karpas
16:45   AUPO – Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm
Robin Schmöcker, Alexander Dockhorn and Bodo Rosenhahn
16:30   Multi-Neighborhood Simulated Annealing for the Oven Scheduling Problem
Francesca Da Ros, Luca Di Gaspero, Marie-Louise Lackner, Nysret Musliu and Felix Winter
16:45   Learning Distributed Scheduling via LLM-Augmented Reinforcement Learning
Yun Liu, Yuqi Feng, Jiahao Fan, Shangce Gao and Yanan Sun
17:00 – 17:20 — Industry Talks
Talk A: Eaton
Plenary Room - Pembroke & Herbert
From Optimization to Scheduling: Practical Lessons in Building Energy Management
Scott McDonald
Talk B: Hexaly
Breakout Room - Lansdowne
Hexaly, a New Kind of Global Optimization Solver
Léa Petit‑Jean Genat
17:20 – 18:45 — Poster and Demo Session — Fitzwilliam Suites & Pre-Function Area

Wednesday, July 1, 2026 — Main Conference Day 2 ↑ Back to Navigation

09:00 – 10:00 — Invited Talk: Nora Ayanian — Plenary Room - Pembroke & Herbert
10:00 – 10:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
10:30 – 12:00 — Morning Sessions
Session 4A: Classical Planning II and Dynamic Programming
Plenary Room - Pembroke & Herbert — Chair: Álvaro Torralba
10:30   Planning as Goal Recognition: Deriving Heuristics from Intention Models
Giacomo Rosa, Jean Honorio, Nir Lipovetzky and Sebastian Sardina
10:45   Policy Comparison Oracles for Action Policy Testing
Ben Sievers, Jan Eisenhut and Jörg Hoffmann
10:55   Counting and Reasoning with Plans
David Speck, Markus Hecher, Daniel Gnad, Johannes K. Fichte and Augusto B. Corrêa
11:05   Finding Optimal Cost-Bounded Plan Reductions
Martha Del Toro, Raquel Fuentetaja and Ángel García-Olaya
Session 4B: Human-Aware Planning
Breakout Room - Lansdowne — Chair: Ron Petrick
10:30   MO-VLA: Preference Adaptation for Vision-Language-Action Models via Multi-Objective Reinforcement Learning
Yan Yang, Mingxuan Jing and Yuquan Wu
10:45   How Humans Explain the Difference in the Quality of Plans — A User Study
Benjamin Krarup, Amanda Coles, Dancheng Gao, Derek Long and David Smith
11:00   Finding Human-Aligned Abstractions Efficiently for Explaining Plan Quality Differences
Benjamin Krarup, Amanda Coles, Derek Long and David Smith
11:15   Domain-Independent Dynamic Programming with Constraint Propagation
Imko Marijnissen, Christopher Beck, Emir Demirović and Ryo Kuroiwa
11:30   Operator-Counting Heuristics for Domain-Independent Dynamic Programming
Anubhav Singh, Florian Pommerening, Tanja Schindler, J. Christopher Beck and Malte Helmert
11:45   When both Grounding and not Grounding are Bad — A Partially Grounded Encoding of Planning into SAT
João Sá and Gregor Behnke
11:15   Markovian Models Anxious to Stay on the Beaten Path: A Psychology-Grounded Approach to Minimising Exposure to Path Uncertainty
Loïs Vanhée and Anais de Graaf
11:30   Compiling Model Reconciliation Explanation Problems into Stackelberg and FOND Planning Problems
Sarath Sreedharan and Pascal Bercher
11:45   Proactive Assistance Agent with Online Goal Recognition
Qihao Shen, Guang Hu and Chenyuan Zhang
12:00 – 13:30 — — Sussex Restaurant
13:30 – 15:00 — Afternoon Sessions
Session 5A: Temporal and Numeric Planning
Plenary Room - Pembroke & Herbert — Chair: David E. Smith
13:30   Compiling Expressive Planning With Data Types
Joan Espasa Arxer, Mateu Villaret, Ian Miguel and Carla Davesa Sureda
13:45   On-Demand Mutex Constraints for Numeric Planning as SMT
Joan Espasa Arxer, Miquel Bofill, Mateu Villaret and Mustafa Faisal
13:55   Compiling Temporal Numeric Planning into Discrete PDDL+
Andrea Micheli, Enrico Scala and Alessandro Valentini
14:05   Subgoaling Relaxation-Based Heuristics for Numeric Planning with Infinite Actions
Ángel Aso-Mollar, Diego Aineto, Enrico Scala and Eva Onaindia
14:20   Cartesian Abstraction Refinement for Simple Numeric Planning
Tanja Schindler, David Speck and Malte Helmert
14:30   Symbolic Pattern Planning
Matteo Cardellini, Enrico Giunchiglia and Marco Maratea
14:45   PING: A Physics-Informed Neuro-Symbolic Generator for Continuous-Time Planning
Mahyar Jahani Nasab, Hamid Rezatofighi, Mor Vered and Buser Say
Session 5B: Learning and Planning
Breakout Room - Lansdowne — Chair: Ayal Taitler
13:30   Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning
Mikoto Kudo, Takumi Tanabe, Akifumi Wachi and Youhei Akimoto
13:45   Mitigating Deception and Interference in Online Goal Recognition Systems
Lorenzo Serina, Mattia Chiari, Matteo Olivato, Luca Putelli, Nicholas Rossetti, Ivan Serina and Alfonso Emilio Gerevini
13:55   Relational Neurosymbolic Markov Models
Lennert De Smet, Gabriele Venturato, Luc De Raedt and Giuseppe Marra
14:05   Beyond Hard Constraints: Budget-Conditioned Reachability for Safe Offline Reinforcement Learning
Janaka Brahmanage and Akshat Kumar
14:20   Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions
Nicola J. Müller, Moritz Oster, Isabel Valera, Jörg Hoffmann and Timo P. Gros
14:30   QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning
Yuanjun Li, Bin Zhang, Hao Chen, Zhouyang Jiang, Dapeng Li and Zhiwei Xu
14:45   Beyond Message Passing: Modern GNN Architectures for Online Planner Selection
Jana Vatter, Ruben Mayer, Hans-Arno Jacobsen, Horst Samulowitz and Michael Katz
15:00 – 15:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
15:30 – 17:30 — Community Meeting and Awards — Plenary Room - Pembroke & Herbert
17:30 – 18:10 — IPC Results — Plenary Room - Pembroke & Herbert
19:15 – Late — Conference Banquet — Guinness Storehouse (Buses depart Conference Hotel at 19:15)

Thursday, July 2, 2026 — Main Conference Day 3 ↑ Back to Navigation

09:00 – 10:00 — Invited Talk: Pascal Bercher — Plenary Room - Pembroke & Herbert
10:00 – 10:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
10:30 – 12:00 — Morning Sessions
Session 6A: Complexity
Plenary Room - Pembroke & Herbert — Chair: Gregor Behnke
10:30   Reversibility and Reachability in HTN Planning: Formalization and Computational Complexities in the Totally-Ordered Setting
Jakub Med, Mohammad Yousefi, Lukas Chrpa and Pascal Bercher
10:45   I Always Told My Mom That Order Is Overrated: Unordered HTN Planning is in PSPACE and Models Problems Beyond STRIPS Best Student Paper
Pascal Lauer, Yifan Zhang, Patrik Haslum and Pascal Bercher
11:00   PDDL Axioms Are Equivalent to Least Fixed Point Logic
Claudia Grundke and Gabriele Röger
11:15   Computing Planning Width: How Hard is it, Really?
Jiajia Song, Seeun William Umboh, Malte Helmert, Nir Lipovetzky and Sebastian Sardina
11:30   Relaxing is Hard: Complexity Results for Lifted Partial Order Causal Link Planning
Harrison Oates and Pascal Bercher
11:45   Complexity Results for Fixing Classical Models Using LTL to Express Which Solutions Are (Un)Desired
Huanghua Sheng and Pascal Bercher
Session 6B: Robotics
Breakout Room - Lansdowne — Chair: Nick Hawes
10:30   Interleaving Scheduling and Motion Planning with Incremental Learning of Symbolic Space-Time Motion Abstractions
Elisa Tosello, Arthur Bit-Monnot, Davide Lusuardi, Alessandro Valentini and Andrea Micheli
10:45   Concrete multi-agent path planning enabling kinodynamically aggressive maneuvers
Keisuke Okumura, Guang Yang, Zhan Gao, Heedo Woo and Amanda Prorok
11:00   SaferSAC: A Deep Reinforcement Learning Framework for Autonomous Obstacle Avoidance Navigation in UAVs
Kaibo Su and Kun Zhu
11:15   DGV: Fusing Dynamic Graphs and Vision-Language Models for Collaborative Dual-Arm Task Planning
Yapeng Pang, Junjie Xu, Zhidong Qiao, Peng Du and Xinyu Zhang
11:30   Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement
Ashish Malik, Caleb Lowe, Aayam Shrestha, Stefan Lee, Fuxin Li and Alan Fern
11:45   Temporally Decoupled Diffusion Planning for Autonomous Driving
Xiang Li, Bikun Wang, John Zhang and Jianjun Wang
12:00 – 13:30 — — Sussex Restaurant
13:30 – 15:05 — Afternoon Sessions
Session 7A: Agentic AI, Gen AI, and Foundation Models for Planning
Plenary Room - Pembroke & Herbert — Chair: Christian Muise
13:30   Self-Improvement for Fast, High-Quality Plan Generation
Robert Gieselmann, Henrike von Huelsen, Mihai Samson, Marie-Christine Meyer, Dariusz Piotrowski, Oleksandr Radomskyi, Justin Okamoto, Turan Gojayev, Michael Painter, Gavin Brown, Federico Pecora and Jeremy Wyatt
13:45   Automating Thought of Search: A Journey Towards Soundness and Completeness
Daniel Cao, Michael Katz, Harsha Kokel, Kavitha Srinivas and Shirin Sohrabi
14:00   Planning in the LLM Era: Building for Reliability and Efficiency
Michael Katz, Harsha Kokel, Kavitha Srinivas and Shirin Sohrabi
14:10   Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning
Leonid Ugadiarov, Yuri Kuratov, Aleksandr Panov and Alexey Skrynnik
14:20   GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models
Andrew Murray, Danial Dervovic, Alberto Pozanco and Michael Cashmore
14:35   Improved Generalized Planning with LLMs through Strategy Refinement and Reflection
Katharina Stein, Nils Hodel, Daniel Fišer, Jörg Hoffmann, Michael Katz and Alexander Koller
14:50   Successor-Generator Planning with LLM-generated Heuristics
Alexander Tuisov, Yonatan Vernik and Alexander Shleyfman
Session 7B: MAPF
Breakout Room - Lansdowne — Chair: Nora Ayanian
13:30   db-LaCAM: Fast and Scalable Multi-Robot Kinodynamic Motion Planning with Discontinuity-Bounded Search and Lightweight MAPF
Akmaral Moldagalieva, Keisuke Okumura, Amanda Prorok and Wolfgang Hoenig
13:45   Polynomial-Time Configuration Generator for Connected Unlabeled Multi-Agent Pathfinding
Takahiro Suzuki and Keisuke Okumura
14:00   LaCAM* Variants for Minimizing Makespan in Multi-Agent Path Finding
Omer Idgar, Dor Atzmon and Ariel Felner
14:10   Enhancing Lifelong Multi-Agent Path-Finding by Using Artificial Potential Fields
Arseni Pertzovskiy, Roni Stern, Ariel Felner and Roie Zivan
14:20   Sampling-Based Multi-Agent Path Planning Guided by Spatio-Temporal Logic Mission Objectives
Vidisha Kudalkar, Sujit Ponguluri, Anand Balakrishnan and Jyotirmoy Deshmukh
14:35   Dynamic Shelf Arrangement and Task Assignment with Stable Matching for Multi-Agent Pickup and Delivery with Multi-Item Packing Problem
Yosuke Fujisawa, Yusaku Wakasugi, Kazuya Nakazawa, Ryo Matsubara and Toshiharu Sugawara
14:50   Analyzing Planner Design Trade-Offs for MAPF under Realistic Simulation
Jingtian Yan, Zhifei Li, William Kang, Stephen Smith and Jiaoyang Li
15:05 – 15:30 — Coffee Break — Fitzwilliam Suites & Pre-Function Area
15:30 – 16:30 — Afternoon Sessions
Session 8A: Plan Execution under Uncertainty
Plenary Room - Pembroke & Herbert — Chair: Andrea Micheli
15:30   Incremental LTLf Synthesis
Giuseppe De Giacomo, Yves Lespérance, Gianmarco Parretti, Fabio Patrizi and Moshe Y. Vardi
15:45   Robust Crop Planning under Uncertainty: Aligning Economic Optimality with Agronomic Sustainability
Runhao Liu, Ziming Chen, You Li and Peng Zhang
16:00   Optimal Clifford Synthesis as Planning
Irfansha Shaik and Jaco van de Pol
16:15   GammaZero: Learning to Guide Belief-Space Search for Long-Horizon POMDPs with Generalizable Graph Representations
Rajesh Mangannavar and Prasad Tadepalli
Session 8B: Applications II
Breakout Room - Lansdowne — Chair: Rick Freedman
15:30   Fully Packed and Ready to Go: High-Density, Rearrangement-Free, Grid-Based Storage and Retrieval
Tzvika Geft, Kostas Bekris and Jingjin Yu
15:45   Automated Planning for Production Routines in Semiconductor Manufacturing
Gianluca Zavan, Konstantin Schekotihin and Thomas Langreiter
16:00   Rating Composite AI Models for Robustness Through Probabilistic Planning
Kausik Lakkaraju, Sunandita Patra, Parisa Zehtabi and Biplav Srivastava
16:15   RASO: Role-Aware Shared Reflection for Multi-Agent Orchestration in E-Commerce Long-Horizon Planning
Kangjia Niu, Yanning Zhang, Xiuchong Wang, Chennan Ma, Siqi Hong, Hankz Hankui Zhuo, Junxiong Zhu and Bo Zheng