mlsanityData to 7 Oct 2026

PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent

arXiv 2202.00531 ↗First posted 1 Feb 2022cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We consider the problem of multi-task reasoning (MTR), where an agent can solve multiple tasks via (first-order) logic reasoning. This capability is essential for human-like intelligence due to its strong generalizability and simplicity for handling multiple tasks. However, a major challenge in developing effective MTR is the intrinsic conflict between reasoning capability and efficiency. An MTR-capable agent must master a large set of "skills" to tackle diverse tasks, but executing a particular task at the inference stage requires only a small subset of immediately relevant skills. How can we maintain broad reasoning capability and also efficient specific-task performance? To address this problem, we propose a Planner-Reasoner framework capable of state-of-the-art MTR capability and high efficiency. The Reasoner models shareable (first-order) logic deduction rules, from which the Planner selects a subset to compose into efficient reasoning paths. The entire model is trained in an end-to-end manner using deep reinforcement learning, and experimental studies over a variety of domains validate its effectiveness.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 42 of its 116 references that are in the map. First posted on arXiv 1 Feb 2022.

Builds on

42 of 116 references.

References · 42

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  5. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  6. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  7. 2017A Survey on Multi-Task Learningcited by 838
  8. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  9. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  10. 2015Policy Distillationcited by 414
  11. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  12. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
30 more
  1. 2018How Does Batch Normalization Help Optimization?cited by 355
  2. 2017A simple neural network module for relational reasoningcited by 345
  3. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  4. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 259
  5. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  6. 2017Learning Explanatory Rules from Noisy Datacited by 210
  7. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 200
  8. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  9. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  10. 2019Neural Logic Machinescited by 144
  11. 2017Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observabilitycited by 143
  12. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  13. 2020Inductive logic programming at 30: a new introductioncited by 83
  14. 2018Relational Deep Reinforcement Learningcited by 72
  15. 2017Recurrent Relational Networkscited by 71
  16. 2017Multi-Task Learning for Contextual Banditscited by 47
  17. 2020Turning 30: New Ideas in Inductive Logic Programmingcited by 42
  18. 2018Iterative Visual Reasoning Beyond Convolutionscited by 38
  19. 2019Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Datacited by 38
  20. 2020Neural Logic Reasoningcited by 38
  21. 2019Synthesizing Datalog Programs Using Numerical Relaxationcited by 23
  22. 2021Differentiable Logic Machinescited by 18
  23. 2015Multi-domain Dialog State Tracking using Recurrent Neural Networkscited by 14
  24. 2015Convex Learning of Multiple Tasks and their Structurecited by 13
  25. 2019Multitask Soft Option Learningcited by 13
  26. 2014Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Networkcited by 11
  27. 2018Learning sparse relational transition modelscited by 11
  28. 2019Attentive Multi-Task Deep Reinforcement Learningcited by 8
  29. 2020Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shiftingcited by 6
  30. 2017Learning to Multi-Task by Active Samplingcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
  2. 2026Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
  3. 2026Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
  4. 2025PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
  5. 2026AdaTIR: Adaptive Tool-Integrated Reasoning via Difficulty-Aware Policy Optimization
  6. 2025AlphaApollo: A System for Deep Agentic Reasoning
  7. 2026Adaptive Latent Agentic Reasoning
  8. 2026STAR-P'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision