mlsanityData to 14 Oct 2026

Task-Agnostic Experts Composition for Continual Learning

arXiv 2506.15566 ↗First posted 18 Jun 2025cs.LGcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more efficient and sustainable AI framework. We propose a compositional approach by ensembling zero-shot a set of expert models, assessing our methodology using a challenging benchmark, designed to test compositionality capabilities. We show that our Expert Composition method is able to achieve a much higher accuracy than baseline algorithms while requiring less computational resources, hence being more efficient.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 8 of its 15 references that are in the map. First posted on arXiv 18 Jun 2025.

Builds on

8 of 15 references.

References · 8

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2016Learning without Forgettingcited by 2,496
  5. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  6. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  7. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  8. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability
  2. 2026Emergent Compositional Skills in Mixture-of-Experts VLAs
  3. 2025A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
  4. 2026When Is Compositional Reasoning Learnable from Verifiable Rewards?
  5. 2026Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
  6. 2023Dynamic MOdularized Reasoning for Compositional Structured Explanation Generation
  7. 2026Hierarchical Compositionality for An Assistive AI Agent
  8. 2024A Second-Order Perspective on Model Compositionality and Incremental Learning