What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity

• URL: http://arxiv.org/abs/2609.17515v1
• Date: Tue, 15 Sep 2026 17:51:48 GMT
• Title: What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
• Abstract summary: Pruning can reduce the deployment cost of large language models, but its impact on context-grounded tool calling remains poorly understood.<n>We systematically study pruning-induced degradation in smart-home tool calling across four large language models (LLMs)<n>Our results show that dense models have narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning.
• Score: 0.9666308705700454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We systematically study pruning-induced degradation in smart-home tool calling across four LLMs spanning dense Transformer, dense hybrid, and mixture-of-experts (MoE) architectures, together with depth, width, hybrid, and expert pruning methods. After post-pruning supervised fine-tuning (SFT), we evaluate more than 19,500 instances from three smart-home datasets. Beyond aggregate task accuracy, we characterize degradation along two dimensions: action components (i.e., operation, device, argument, and value) and task complexity. Our results show that dense models have narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning. Pruning degrades grounded specificity before schema-level intent, and aggressive dense pruning can induce systematic over-refusal. These findings highlight the importance of evaluating pruning beyond aggregate accuracy when selecting pruned LLMs for reliable tool execution.

Related papers

• When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents [48.32450507410869]
  Existing benchmarks evaluate Tool-Integrated Reasoning in LLMs on idealized ''happy paths''<n>We introduce ToolMaze, a benchmark for dynamic path discovery and error recovery in TIR agents.
  arXiv  Detail & Related papers  (2026-06-04T07:38:46Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• What Makes a Good LLM Agent for Real-world Penetration Testing? [37.56537537883771]
  We analyze 28 LLM-based penetration testing systems and evaluate five representative implementations across three benchmarks of increasing complexity.<n>We show that Type B failures share a root cause that is largely invariant to the underlying LLM: agents lack real-time task difficulty estimation.<n>We present Excalibur, a penetration testing agent that couples strong tooling with difficulty-aware planning.
  arXiv  Detail & Related papers  (2026-02-19T18:42:40Z)
• Breaking Expert Knowledge Limits: Self-Pruning for Large Language Models [21.22854931342453]
  Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size.<n>Existing pruning methods rely heavily on manual design pruning algorithms, thereby leading to textithuge labor costs and textitrequires expert knowledge.<n>We propose a novel pruning method called textbfAutoPrune, which first overcomes expert knowledge limits by leveraging LLMs to design optimal pruning algorithms for themselves automatically without any expert knowledge.
  arXiv  Detail & Related papers  (2025-11-19T12:38:21Z)
• High-Layer Attention Pruning with Rescaling [14.141903038286362]
  Pruning is a highly effective approach for compressing large language models (LLMs)<n>We propose a novel pruning algorithm that strategically prunes attention heads in the model's higher layers.<n>We conduct comprehensive experiments on a wide range of LLMs, including LLaMA3.1-8B, Mistral-7B-v0.3, Qwen2-7B, and Gemma2-9B.
  arXiv  Detail & Related papers  (2025-07-02T17:15:05Z)
• Growing Through Experience: Scaling Episodic Grounding in Language Models [67.27024505353384]
  Language models (LMs) require robust episodic grounding to excel at physical planning tasks.<n>Current episodic grounding approaches struggle with scalability and integration.<n>We propose a scalable weak-to-strong episodic learning framework that effectively transfers episodic behaviors from smaller to larger LMs.
  arXiv  Detail & Related papers  (2025-06-02T04:52:19Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining [16.026565606764954]
  We simplify the pruning process for Transformer-based large language models (LLMs) We propose two inference-aware pruning criteria derived from the optimization perspective of output approximation. We also introduce a two-step reconstruction technique to mitigate pruning errors without model retraining.
  arXiv  Detail & Related papers  (2024-07-26T23:53:59Z)
• A deeper look at depth pruning of LLMs [49.30061112976263]
  Large Language Models (LLMs) are resource-intensive to train but more costly to deploy in production. Recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance. We show that adaptive metrics exhibit a trade-off in performance between tasks.
  arXiv  Detail & Related papers  (2024-07-23T08:40:27Z)

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.