Latent Action Reparameterization for Efficient Agent Inference

• URL: http://arxiv.org/abs/2605.18597v2
• Date: Tue, 19 May 2026 03:38:49 GMT
• Title: Latent Action Reparameterization for Efficient Agent Inference
• Abstract summary: We propose a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior.<n>Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model.
• Score: 56.42014061367112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through system-level optimizations or prompt engineering, we argue that a key bottleneck lies in the representation of the action space itself. We propose Latent Action Reparameterization (LAR), a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior. By reparameterizing agent actions into latent units, LAR enables decision making over a shorter effective horizon while preserving the expressiveness of the original action space. Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model, allowing both planning and execution to operate over abstract action representations. Across a range of LLM-based agent benchmarks, LAR significantly reduces the effective action horizon and improves inference efficiency under fixed compute budgets. As a consequence, our approach achieves substantial reductions in action tokens and corresponding wall-clock inference time, while maintaining or improving task success rates. These results suggest that action representation learning is a critical and underexplored factor in scaling efficient LLM agent inference, complementary to advances in model architecture and hardware.

Related papers

• Strategy-Aware Parameter-Efficient Adaptation for LLM-based Auto-Bidding [16.834816807572757]
  SAGE is a novel Strategy-aware Auto-bidding framework guided by LLMs for efficient bidding.<n>We show that SAGE consistently achieves superior performance while tuning less than 10% of the trainable parameters required by full fine-tuning.
  arXiv  Detail & Related papers  (2026-07-27T10:08:43Z)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• DEAS: DEtached value learning with Action Sequence for Scalable Offline RL [46.40818333031899]
  Action Sequence (DEAS) is a simple yet effective offline RL framework that leverages action sequences for value learning.<n>DEAS consistently outperforms baselines on complex, long-horizon tasks from OGBench.<n>It can be applied to enhance the performance of large-scale Vision-Language-Action models.
  arXiv  Detail & Related papers  (2025-10-09T03:11:09Z)
• Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning [53.35553353785948]
  Motivated by the puzzling observation that inserting long sequences of meaningless tokens before the query prompt can consistently enhance reasoning LLM performance, this work analyzes the underlying mechanism driving this phenomenon.<n>We find that the improvements arise from a redistribution of activations in the LLM's layers, where near zero activations become less frequent while large magnitude activations increase.<n>We propose a lightweight inference-time technique that modifies activations directly without altering the input sequence.
  arXiv  Detail & Related papers  (2025-10-01T15:39:38Z)
• SAND: Boosting LLM Agents with Self-Taught Action Deliberation [54.48979740613828]
  Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts.<n>We propose Self-taught ActioN Deliberation (SAND) framework, enabling LLM agents to explicitly deliberate over candidate actions before committing to one.<n>SAND achieves an average 20% improvement over initial supervised finetuning and also outperforms state-of-the-art agent tuning approaches.
  arXiv  Detail & Related papers  (2025-07-10T05:38:15Z)
• Structured Agent Distillation for Large Language Model [56.38279355868093]
  We propose Structured Agent Distillation, a framework that compresses large LLM-based agents into smaller student models.<n>Our method segments trajectories into [REASON] and [ACT] spans, applying segment-specific losses to align each component with the teacher's behavior.<n>Experiments on ALFWorld, HotPotQA-ReAct, and WebShop show that our approach consistently outperforms token-level and imitation learning baselines.
  arXiv  Detail & Related papers  (2025-05-20T02:01:55Z)
• CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models [37.476241509187304]
  Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data.<n>The lack of interpretability in their underlying mechanisms limits the ability to effectively steer LLMs for specific applications.<n>We introduce an efficient selective layer intervention based on prominent parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-10-23T09:40:15Z)
• GLANCE: Global Actions in a Nutshell for Counterfactual Explainability [10.25011737760687]
  We introduce GLANCE, a versatile and adaptive framework, comprising two algorithms. C-GLANCE employs a clustering approach that considers both the feature space and the space of counterfactual actions. T-GLANCE provides additional features to enhance flexibility.
  arXiv  Detail & Related papers  (2024-05-29T09:24:25Z)
• Discrete Action On-Policy Learning with Action-Value Critic [72.20609919995086]
  Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension. We construct a critic to estimate action-value functions, apply it on correlated actions, and combine these critic estimated action values to control the variance of gradient estimation. These efforts result in a new discrete action on-policy RL algorithm that empirically outperforms related on-policy algorithms relying on variance control techniques.
  arXiv  Detail & Related papers  (2020-02-10T04:23:09Z)

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.