Diagnosing Compositional Generalization in Sequential Robot Tasks

• URL: http://arxiv.org/abs/2607.29687v1
• Date: Fri, 31 Jul 2026 17:59:59 GMT
• Title: Diagnosing Compositional Generalization in Sequential Robot Tasks
• Abstract summary: This paper studies compositional generalization through the lens of instruction-space coverage.<n>We decompose the generalization gap into three sources: textitmarginal instruction shift, textitinstruction-compositional shift, and textitcontext-action shift
• Score: 47.24821158025177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential robot manipulation requires policies to execute novel combinations of familiar instruction components. However, collecting demonstrations for all possible instruction tuples is combinatorially expensive, while sparsely covered datasets often fail under out-of-distribution recombination. This paper studies compositional generalization through the lens of instruction-space coverage. We decompose the generalization gap into three sources: \textit{marginal instruction shift}, \textit{instruction-compositional shift}, and \textit{context--action shift}. This decomposition allows us to diagnose when sparse training coverage is sufficient, and what structure the training set must preserve for reliable action prediction. Our results show that exhaustive tuple enumeration is unnecessary: a structured subset, as small as one quarter of the full task space, can recover strong out-of-distribution performance when it covers action-relevant dependencies. We further find that sparse training often fails due to instruction steering rather than missing low-level skills; finetuning only one demonstration per task improves OOD success from \(0.4\%\) to \(54.7\%\). For semantically dependent tasks, effective coverage must capture relational structure rather than only factor diversity. These findings suggest that efficient robot data collection should prioritize dependency coverage in instruction space over exhaustive task expansion. More results are available in the supplementary material. Project website: https://yixiaowang7.github.io/Diagnosing_Compositional_Generalization_Robot_Page/.

Related papers

• TaPeR: Probabilistic Recovery of Sparse Task Precedence Graphs from a Handful of Demonstrations [16.604293152314995]
  Long-horizon manipulation tasks are often only partially ordered.<n>Existing approaches typically infer task structure from human demonstrations using both temporal and symbolic supervision.<n>We present an approach for extracting task dependency structures from demonstrations using only simple kinematic graphs and distributions over relative object poses.
  arXiv  Detail & Related papers  (2026-08-21T12:31:50Z)
• Learning Composable Chains-of-Thought [57.73731224510169]
  We train large language models (LLMs) to reason on chain-of-thought (CoT) traces of in-distribution reasoning problems.<n>We take a step towards compositional generalization of reasoning skills when addressing a target compositional task that has no labeled CoT data.<n>We can train "atomic CoT" models on the atomic tasks with Composable CoT data and combine them with multitask learning or model merging for better zero-shot performance on the target compositional task.
  arXiv  Detail & Related papers  (2025-05-28T17:51:10Z)
• Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains [0.565395466029518]
  We propose a novel pretext task based on the classical binning method. The idea is straightforward: reconstructing the bin indices (either orders or classes) rather than the original values. Our empirical investigations ascertain several advantages of binning.
  arXiv  Detail & Related papers  (2024-05-13T01:23:14Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks [86.10875837475783]
  Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. Existing neural models have been shown to lack this basic ability in learning symbolic structures. We propose two auxiliary sequence prediction tasks that track the progress of function and argument semantics.
  arXiv  Detail & Related papers  (2021-09-30T16:41:19Z)
• Meta-Learning to Compositionally Generalize [34.656819307701156]
  We implement a meta-learning augmented version of supervised learning. We construct pairs of tasks for meta-learning by sub-sampling existing training data. Experimental results on the COGS and SCAN datasets show that our similarity-driven meta-learning can improve generalization performance.
  arXiv  Detail & Related papers  (2021-06-08T11:21:48Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)
• Hierarchical Reinforcement Learning as a Model of Human Task Interleaving [60.95424607008241]
  We develop a hierarchical model of supervisory control driven by reinforcement learning. The model reproduces known empirical effects of task interleaving. The results support hierarchical RL as a plausible model of task interleaving.
  arXiv  Detail & Related papers  (2020-01-04T17:53:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.