ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer

• URL: http://arxiv.org/abs/2604.08355v2
• Date: Fri, 10 Apr 2026 04:24:05 GMT
• Title: ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
• Abstract summary: Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered.<n>We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning.<n>Our approach achieves zero-shot transfer across a broad spectrum of complex and truly novel analogous tasks, moving beyond the limitations of fixed category mappings.
• Score: 10.492383929472734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer, they are often constrained by predefined, discrete class systems, limiting their adaptability to novel or compositional task variations. We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning via a text-conditioned Variational Autoencoder (VAE). Our core innovation utilizes a Large Language Model (LLM) as a dynamic \textit{semantic operator} at test time. Rather than relying on rigid rules, our agent queries the LLM to semantically remap the description of the current observation to align with the source task. This source-aligned caption conditions the VAE to generate an imagined state compatible with the agent's original training, enabling direct policy reuse. By harnessing the flexible reasoning capabilities of LLMs, our approach achieves zero-shot transfer across a broad spectrum of complex and truly novel analogous tasks, moving beyond the limitations of fixed category mappings. Code and videos are available \href{https://anonymous.4open.science/r/ASPECT-85C3/}{here}.

Related papers

• Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions [61.479946958462754]
  We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy.<n>We present a novel task embedding technique leveraging a new generation of semantic translations-to-automata.
  arXiv  Detail & Related papers  (2026-02-06T14:46:27Z)
• Policy-Conditioned Policies for Multi-Agent Task Solving [53.67744322553693]
  In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
  arXiv  Detail & Related papers  (2025-12-24T07:42:10Z)
• From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation [3.75886080255807]
  We introduce two innovative attack frameworks designed to generate dynamic and adaptive adversarial examples.<n>We produce subtle and natural-looking adversarial inputs that preserve semantic similarity to the original text.<n>Our attacks evolve with the advancements in LLMs and demonstrate strong transferability acrossversa unknown to the attacker.
  arXiv  Detail & Related papers  (2025-11-05T02:27:56Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation [89.65955788873532]
  Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP)<n>We propose a novel framework named GenKI, which aims to improve the OpenQA performance by exploring Knowledge Integration and controllable Generation.
  arXiv  Detail & Related papers  (2025-05-26T08:18:33Z)
• Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching [17.76990521486307]
  Deep Reinforcement Learning models often fail to generalize when even small changes occur in the environment's observations or task requirements.<n>We propose a zero-shot method for mapping between latent spaces across different agents trained on different visual and task variations.<n>We empirically demonstrate zero-shot stitching performance on the CarRacing environment with changing background and task.
  arXiv  Detail & Related papers  (2025-02-26T22:06:00Z)
• Analyzing Finetuning Representation Shift for Multimodal LLMs Steering [56.710375516257876]
  We propose to map hidden states to interpretable visual and textual concepts.<n>This enables us to more efficiently compare certain semantic dynamics, such as the shift from an original and fine-tuned model.<n>We also demonstrate the use of shift vectors to capture these concepts changes.
  arXiv  Detail & Related papers  (2025-01-06T13:37:13Z)
• Efficient Transfer Learning for Video-language Foundation Models [13.166348605993292]
  We propose a parameter-efficient Multi-modalpatio Ssupervised-Temporal Adapter (MSTA) to enhance alignment between textual and visual representations.<n>We evaluate the effectiveness of our approach across four tasks: zero-shot transfer, few-shot learning, base-to-novel generalization, and fully-Temporal learning.
  arXiv  Detail & Related papers  (2024-11-18T01:25:58Z)
• CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning [17.614980614656407]
  We propose Continual Generative training for Incremental prompt-Learning. We exploit Variational Autoencoders to learn class-conditioned distributions. We show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities.
  arXiv  Detail & Related papers  (2024-07-22T16:51:28Z)
• Integrating LLMs and Decision Transformers for Language Grounded Generative Quality-Diversity [0.0]
  Quality-Diversity is a branch of optimization that is often applied to problems from the Reinforcement Learning and control domains. We propose a Large Language Model to augment the repertoire with natural language descriptions of trajectories. We also propose an LLM-based approach to evaluating the performance of such generative agents.
  arXiv  Detail & Related papers  (2023-08-25T10:00:06Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)

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.