AN AACL–IJCNLP 2026 WORKSHOP

From Reasoning
to Agency.

Learning, Acting, and Adapting
with Foundation Models

Beyond generating answers. Toward systems that
reason, act, and learn from the world.

November 9–10, 2026Workshop window · exact day TBA
Hengqin, Zhuhai, ChinaJust across the water from Macau
How foundation models learn, act, and adaptA foundation model reasons and plans at the center of a continuous loop. It learns from data and experience, acts through tools and environments, and adapts using feedback and memory. Outcomes improve its next action.knowledgeactionsfeedbackFoundation modelREASON · PLAN01LearnData &experienceBuild useful knowledge02ActTools &environmentsPut plans into motion03AdaptFeedback &memoryImprove the next step
INTELLIGENCE, IN THE LOOP
CALL FOR PAPERS

Ideas that connect reasoning to real-world agency.

Submission deadline Sep 30, 2026

Reasoning is a beginning.
Agency is the next step.

Foundation models are becoming more capable reasoners. The next challenge is to turn that capability into purposeful action: making plans, using tools, interacting with environments, and learning from experience.

This workshop brings together the NLP, machine learning, and agentic AI communities to study that transition. We ask how reasoning supports action, how interaction creates new learning opportunities, and how agents can adapt reliably over time.

Find your research direction

Reason with purpose

From inference to plans and decisions.

Act in the world

From text to tools and environments.

Adapt through experience

From feedback to lasting improvement.

Many directions.
One connected conversation.

We welcome work across the full path from
reasoning to agency, including but not limited
to the following themes.

06 research themes
/01

Reasoning & planning

Turning deliberation into decisions that work beyond a single response.

  • Chain-of-thought, search, and test-time scaling
  • Long-horizon planning and task decomposition
  • World models, causal and multimodal reasoning
DELIBERATIONPLANNING
/02

Learning to act

Learning effective behavior from feedback, demonstrations, and interaction.

  • Reinforcement learning and verifiable rewards
  • Imitation learning and trajectory optimization
  • Process supervision and synthetic experience
REINFORCEMENT LEARNINGFEEDBACK
/03

Tools & environments

Connecting foundation models to tools, computers, and the physical world.

  • Tool use, function calling, and orchestration
  • Web, coding, and computer-use agents
  • Embodied agents and multimodal interaction
TOOL USEINTERACTION
/04

Memory & adaptation

Building agents that retain experience and improve as their worlds change.

  • Episodic memory and context management
  • Continual learning and test-time adaptation
  • Self-reflection, skill discovery, and transfer
MEMORYCONTINUAL LEARNING
/05

Multi-agent collaboration

Studying how agents coordinate with each other and collaborate with people.

  • Communication, coordination, and cooperation
  • Collective reasoning and multi-agent learning
  • Human–agent interaction and shared control
COORDINATIONHUMAN + AI
/06

Evaluation & responsible agency

Measuring meaningful progress toward reliable, efficient, and safe agents.

  • Benchmarks, reproducibility, and real-world validity
  • Robustness, safety, alignment, and oversight
  • Interpretability and compute–performance trade-offs
EVALUATIONTRUSTWORTHINESS

Working between these themes? You belong here. We also welcome applications in scientific discovery, software engineering, embodied intelligence, education, and multilingual or low-resource settings.

Bring a new perspective.
Move the field forward.

We invite original contributions that deepen our understanding of foundation models as reasoning, learning, and acting systems.

From a new method to a thoughtful position, from a useful benchmark to an illuminating negative result—there is room for different kinds of progress.

ACL / ARR templateDouble-blind review
Use review mode and anonymize your paper and supplementary materials.
YOUR CONTRIBUTION STARTS HERE

Research & methods

Empirical studies, theoretical insights, new methods, and agent systems.

Perspectives & resources

Position papers, datasets, benchmarks, analyses, and emerging ideas.

Paper submission deadlineSeptember 30, 202611:59 PM Anywhere on Earth (UTC−12)
Submit your paper (opens in a new tab)

Make space
for what’s next.

A few dates for your calendar.
All deadlines are at 11:59 PM AoE
(Anywhere on Earth, UTC−12).

A global community.
One shared deadline.
2026 · WORKSHOP TIMELINE
Call for papersThe conversation begins
Notification of acceptanceDecisions sent to authors
Camera-ready papers dueFinal versions from authors
Proceedings dueOrganizers · if publishing proceedings
See you in HengqinWorkshop window · exact day to be announced

The proceedings deadline applies to organizers, if archival publication is confirmed. Any ARR-specific timeline will be announced separately.

An afternoon of ideas.
And the people behind them.

PRELIMINARY SCHEDULE

Four invited talks, followed by a poster session.
Each talk runs for 20–30 minutes
within a 30-minute slot.

All times in China Standard Time (UTC+8). Exact workshop day to be announced.

Join the workshop online

Zoom meeting ID: 815 4152 2305

Join on Zoom (opens in a new tab)
Preliminary workshop schedule, China Standard Time (UTC+8)
Time (UTC+8)Speaker & session
–Jian Yang InCoder-32B: A Code Foundation Model for Industrial Applications
–Ningyu Zhang Cortex: Consolidating Context into Parametric Memory
–Liwei Liu Exploring the Path from AI4Science to AI4Research
–Zhiqin Yang RobotWorld: Benchmarking Multimodal Agents as Physical Agents
onwardsPoster sessionResearch presentations and discussion

Meet the speakers.

Industrial code, model memory, scientific discovery,
and agents in the physical world.

13:30–14:00 · UTC+8

Jian Yang

Beihang University

InCoder-32B: A Code Foundation Model for Industrial Applications

Industrial code must satisfy constraints that vary across domains. In chip design, code must respect hardware timing semantics. In GPU programming, kernels must compute the correct result while making efficient use of memory. This talk presents InCoder-32B, a 32-billion-parameter code foundation model trained from scratch for applications in chip design, GPU kernel optimization, embedded systems, compiler optimization, and 3D modeling.

The talk will walk through the training pipeline, from pretraining on general-purpose code and further training on curated industrial code to a mid-training stage that introduces synthetic industrial reasoning data and gradually extends the context window from 8K to 128K tokens. It will also cover post-training grounded in actual execution results. Drawing on evaluations across 14 general coding benchmarks and nine industrial benchmarks, the talk will examine how the model balances general programming capabilities with the specialized requirements of industrial tasks.

Speaker biography

Jian Yang is an associate professor in the School of Computer Science and Engineering at Beihang University. His research focuses on large language models for code, model pretraining and post-training, and code understanding and generation. He has published more than 100 papers in leading international journals and at conferences such as ICLR, NeurIPS, ACL, and EMNLP, including more than 30 as first or corresponding author. His work has received over 48,000 citations on Google Scholar.

14:00–14:30 · UTC+8

Ningyu Zhang

Zhejiang University

Cortex: Consolidating Context into Parametric Memory

Large language models can benefit from context, but these gains often disappear once the context is removed. Inspired by biological memory consolidation, we introduce Memory Consolidation (MC) and propose Cortex, a framework that internalizes context-induced improvements into model parameters while preserving existing capabilities. Across diverse model architectures and scales (4B–120B), Cortex achieves strong consolidation and retention. Notably, after 50 sequential edits on a 14B model, Cortex-Structural recovers 88.9% of context-induced gains while retaining 99.8% of original non-target performance.

Speaker biography

Ningyu Zhang, Ph.D., is an associate professor at Zhejiang University and is among Stanford University’s top 2% scientists. His research focuses on natural language processing, large language models, knowledge graphs, and knowledge editing. He has published papers in top academic journals and conferences such as Natural Machine Intelligence, NeurIPS, ICLR, ICML, ACL, and EMNLP. He has developed OceanGPT, DeepKE, EasyEdit, and LightMem. He serves as an Associate Editor for TMLR, Machine Intelligence Research, Neural Networks, and TALLIP. He is also an Area Chair (Senior Area Chair) for ACL, EMNLP, NeurIPS, ICLR, ICML, and KDD.

14:30–15:00 · UTC+8

Liwei Liu

2012 Laboratories, Huawei Technologies Co., Ltd.

Exploring the Path from AI4Science to AI4Research

Artificial intelligence is opening up new ways to understand complex data, predict biological patterns, and accelerate discovery across biology, medicine, and drug development. This talk presents three representative studies from our team: developing an RNA language model through cross-omics semantic learning, pretraining a single-cell model using hundred-million-scale datasets, and developing a bioinformatics agent for automated analysis and interpretation of sequencing-based omics data. Together, these studies explore how AI can extend from learning biological representations and supporting prediction tasks to assisting scientific analysis and automating research workflows.

Speaker biography

Liwei Liu is an AI4Science researcher at the 2012 Laboratories of Huawei Technologies Co., Ltd. Her research focuses on AI applications in biology, medicine, health, and materials science, as well as AI models and agents that support scientific research. Her work has been published in Advanced Science, Chemical Science, Nature Communications, and other journals.

15:00–15:30 · UTC+8

Zhiqin Yang

The Hong Kong University of Science and Technology

RobotWorld: Benchmarking Multimodal Agents as Physical Agents

As multimodal agents excel in digital spaces, empowering them to act as physical agents in the real world remains a grand challenge. In this talk, we introduce RobotWorld, a comprehensive benchmark designed to evaluate general-purpose multimodal agents across 84 diverse tasks and 5 core embodiments (manipulation, mobile manipulation, locomotion, driving, and flight).

Speaker biography

Zhiqin Yang is a PhD student at the Hong Kong University of Science and Technology. His research focuses on reasoning models and robot agents. He is the first author of RobotWorld and an ICML Spotlight paper on preference alignment. His work has also appeared at NeurIPS, ICLR, ICML, and CVPR.

Different perspectives.
Shared curiosity.

Meet the team bringing our community together
across NLP, machine learning, and agentic AI.

Jiaheng Liu

Nanjing University

Yuxiang Ren

Nanjing University

Zhen Zhang

Nanjing University

Yanghai Wang

Nanjing University

Yifan Yao

Nanjing University

Xinping Lei

Nanjing University

Yiyan Ji

Nanjing University

Haoran Yang

Central South University

Jiayi Tian

Alibaba

Tianmu Melody Convention Exhibition Center on an island in the Tianmu River in Hengqin, Zhuhai
HengqinZHUHAI, CHINA
A PLACE TO CONNECT.
Photo: AACL-IJCNLP 2026 (opens in a new tab)
MEET US IN NOVEMBER

New connections.
A beautiful setting.

Join us in Hengqin, Zhuhai, just across the water from Macau, for a meeting of ideas at AACL-IJCNLP 2026.

Tianmu Melody Convention Exhibition CenterMain conference venue · workshop room TBA
Venue & travel information (opens in a new tab)

Before you
submit.

The essentials, in one place.

Is my work a good fit for this workshop?

If your work helps explain or improve how foundation models reason, learn, act, or adapt, we would like to hear from you. We welcome empirical and theoretical work, systems, datasets, benchmarks, position papers, and carefully analyzed negative results. The topic list is illustrative, not exhaustive; connections across research areas are especially welcome.

What are the paper format and review requirements?

Please use the official ACL/ARR template in review mode and submit an anonymized PDF. Review will be double-blind: author identities must not appear in the paper or supplementary materials. Final page limits will be announced here. Please follow the ACL guidance for citations and anonymized artifacts.

Can I submit a paper already reviewed by ARR?

An ACL Rolling Review (ARR) commitment route is under consideration. Eligibility, a dedicated commitment link, and any separate deadline will be published if this route is offered. Until then, September 30, 2026 is the announced paper submission deadline; no ARR extension is confirmed.

Will accepted papers appear in the ACL Anthology?

The publication policy, including whether proceedings will appear in the ACL Anthology, is to be confirmed. Archival status and policies affecting submission of the same work to other venues will be stated in the final guidelines. The October 22 proceedings deadline is for organizers if archival proceedings are produced; it is not an additional author deadline.

When and where will the workshop take place?

The AACL-IJCNLP 2026 workshop window is November 9–10, 2026 in Hengqin, Zhuhai, China, next to Macau. The main conference venue is Tianmu Melody Convention Exhibition Center. Our exact workshop day and room are to be announced. The preliminary program begins at 13:30 China Standard Time (UTC+8), with four invited talks followed by a poster session from 15:30. Online participation is available via the Zoom link in the Program section.