Proposed workshop at NeurIPS 2026

Embodied agents need neural perception, symbolic reasoning, and shared semantics to plan, learn, and act reliably.



About the workshop

NEmo focuses on embodied neuro-symbolic AI: the integration of learned perception, reinforcement learning, large language models, planning, and structured symbolic knowledge in agents that act in physical or richly simulated environments.

Robotic and interactive agents must perceive changing worlds, reason over goals and constraints, execute long action sequences, and recover when assumptions fail. In this setting, hallucinated preconditions, brittle domain models, and ungrounded affordance knowledge become safety and reliability problems.

The workshop is designed for researchers in machine learning, knowledge representation, planning, robotics, human-robot interaction, semantic web, and trustworthy AI who are working on adjacent parts of the same problem.

Target Venue

NeurIPS 2026

Status

Pending

Locations (TBD)

Sydney, Paris, Atlanta



Core Challenges

The programme is organised around three technical challenges.

Long-Horizon Planning

Interfaces for learning, revising, and verifying symbolic action models while learned components handle perception and low-level control.

LLMs and Provenance

Reliable use of LLMs as domain-model elicitors, policy priors, symbolic constraint generators, and natural-language interfaces.

Shared Semantics

Reusable knowledge layers connecting environments, object affordances, robot capabilities, plans, and execution traces.

Topics

  • Neuro-symbolic AI for embodied agents
  • LLMs for planning in atypical domains
  • Knowledge representation for planning
  • Ontological reasoning for embodied applications
  • Tacit planning knowledge in frontier models
  • Symbolic model elicitation for embodied reasoning
  • Perception and sensor grounding
  • Rule-based validation of symbolic domains
  • Neuro-symbolic reinforcement learning
  • Long-horizon planning and plan repair
  • Self-evolving agents
  • Ethical aspects of embodied AI systems


Workshop Format

Planned as a one-day, in-person workshop of roughly 8.5 hours.

Planned Sessions

The format combines invited talks, contributed talks, posters, demos, and structured discussion. Organizers will introduce and moderate; invited talks will come from external speakers.

The goal is to leave the day with a short public report covering open problems, shared assumptions, and candidate benchmarks or semantic layers.

Demos are expected to be laptop-, video-, or browser-based unless additional equipment is secured.

Opening, goals, and audience poll
Invited talk 1 with discussion
Contributed talks I and shared Q&A
Coffee, posters, and demos
Breakouts on the three core challenges
Lunch
Invited talk 2 with discussion
Contributed talks II and shared Q&A
Lightning talks for short papers
Coffee, posters, and demos
Closing synthesis and report planning


Call for Papers

Contributed work is planned as non-archival and managed through OpenReview.

Long Papers

  • Up to 8 pages
  • Original work on embodied neuro-symbolic AI
  • Three reviews per submission
Short Papers

  • Up to 4 pages
  • Position papers, early results, benchmarks, demos
  • Eligible for lightning talks and posters

The call will discourage already-published work, near-duplicates of NeurIPS main-conference presentations, and invited talks reused across workshops.

OpenReview


Important Dates

Draft timeline for planning.

  • Call for papers released: July 2026
  • Submission deadline: Around August 29, 2026
  • Reviews due: Mid-September 2026
  • Notifications sent: Before September 29, 2026
  • Camera-ready materials: October 2026

Final dates will be confirmed after workshop acceptance.


Organizing Committee

The team spans robotics, planning, reinforcement learning, neuro-symbolic AI, semantic web, and knowledge graphs.

Elena Umili

Elena Umili

Sapienza University of Rome

elena.umili@uniroma1.it
Emanuele Musumeci

Emanuele Musumeci

Sapienza University of Rome

emanuele.musumeci@uniroma1.it
Vincenzo Suriani

Vincenzo Suriani

Sapienza University of Rome

vincenzo.suriani@uniroma1.it
Daniel Dobriy

Daniel Dobriy

Vienna University of Economics and Business

daniel.dobriy@wu.ac.at
Anna Sofia Lippolis

Anna Sofia Lippolis

University of Bologna

annasofia.lippolis2@unibo.it


Contact

Venue

NeurIPS 2026, location to be confirmed

Contact Person

Emanuele Musumeci