SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding

• URL: http://arxiv.org/abs/2603.09036v1
• Date: Tue, 10 Mar 2026 00:11:58 GMT
• Title: SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding
• Abstract summary: LM-based agents excel when given high-level action APIs but struggle to ground language into low-level control.<n>We introduce SCALAR, a bidirectional framework coupling LLM planning with RL through a learned skill library.<n>On Craftax, SCALAR achieves 88.2% diamond collection, a 1.9x improvement over the best baseline, and reaches the Gnomish Mines 9.1% of the time where prior methods fail entirely.
• Score: 47.41195092283274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LM-based agents excel when given high-level action APIs but struggle to ground language into low-level control. Prior work has LLMs generate skills or reward functions for RL, but these one-shot approaches lack feedback to correct specification errors. We introduce SCALAR, a bidirectional framework coupling LLM planning with RL through a learned skill library. The LLM proposes skills with preconditions and effects; RL trains policies for each skill and feeds back execution results to iteratively refine specifications, improving robustness to initial errors. Pivotal Trajectory Analysis corrects LLM priors by analyzing RL trajectories; Frontier Checkpointing optionally saves environment states at skill boundaries to improve sample efficiency. On Craftax, SCALAR achieves 88.2% diamond collection, a 1.9x improvement over the best baseline, and reaches the Gnomish Mines 9.1% of the time where prior methods fail entirely.

Related papers

• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates [53.3717573880076]
  We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates.<n>JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.<n>Experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods.
  arXiv  Detail & Related papers  (2026-01-26T14:16:51Z)
• Guiding Exploration in Reinforcement Learning Through LLM-Augmented Observations [0.0]
  Large Language Models (LLMs) possess procedural knowledge and reasoning capabilities from text pretraining.<n>We propose a framework that provides LLM-generated action recommendations through augmented observation spaces.
  arXiv  Detail & Related papers  (2025-10-09T19:54:31Z)
• Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning [16.095629872564874]
  Reinforcement learning is arguably the most prominent fine-tuning method.<n>Evolution strategies (ES) once showed comparable performance to RL on models with a few million parameters.<n>ES can search efficiently over billions of parameters and outperform existing RL fine-tuning methods in multiple respects.
  arXiv  Detail & Related papers  (2025-09-29T07:19:34Z)
• How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve [2.33361323991006]
  Large Language Models (LLMs) are increasingly deployed for narrow tasks in resource-constrained settings.<n>We present LLM-Sieve, a framework that prunes LLMs down to the minimal parameter subset needed to preserve task performance.
  arXiv  Detail & Related papers  (2025-05-23T20:17:20Z)
• Controlling Large Language Model with Latent Actions [27.0292050543406]
  Adapting Large Language Models to downstream tasks using Reinforcement Learning has proven to be an effective approach.<n>This paper studies learning a compact latent action space to enhance the controllability and exploration of RL for LLMs.<n>We propose Controlling Large Language Models with Latent Actions (CoLA), a framework that integrates a latent action space into pre-trained LLMs.
  arXiv  Detail & Related papers  (2025-03-27T11:25:22Z)
• Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning - A Convex Optimization Perspective [55.66517396157806]
  The widely adopted approach in post-training popular open-source LLMs is to sequentially perform SFT and RLHF/DPO.<n>This is suboptimal in terms of SFT and RLHF/DPO trade-off.<n>We propose a practical joint post-training framework which has theoretical convergence guarantees and empirically outperforms sequential post-training framework.
  arXiv  Detail & Related papers  (2024-10-20T19:38:41Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)

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.