Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning

• URL: http://arxiv.org/abs/2512.06250v1
• Date: Sat, 06 Dec 2025 02:50:32 GMT
• Title: Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning
• Abstract summary: This work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance.<n>Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal.<n>Results show 23-55% improvements in completion time, 83% reduction in runtime variance, and 71% improvement in worst-case scenarios.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds between two orthogonal navigation policies. Using maze navigation as a case study, this work demonstrates how an agent can dynamically transition between systematic exploration (coverage) and goal-directed pathfinding (convergence) to improve task performance. Unlike fixed-threshold approaches, the agent uses Q-learning to adapt switching behavior based on coverage percentage and distance to goal, requiring only minimal domain knowledge: maze dimensions and target location. The agent does not require prior knowledge of wall positions, optimal threshold values, or hand-crafted heuristics; instead, it discovers effective switching strategies dynamically during each run. The agent discretizes its state space into coverage and distance buckets, then adapts which coverage threshold (20-60\%) to apply based on observed progress signals. Experiments across 240 test configurations (4 maze sizes from 16$\times$16 to 128$\times$128 $\times$ 10 unique mazes $\times$ 6 agent variants) demonstrate that adaptive threshold learning outperforms both single-strategy agents and fixed 40\% threshold baselines. Results show 23-55\% improvements in completion time, 83\% reduction in runtime variance, and 71\% improvement in worst-case scenarios. The learned switching behavior generalizes within each size class to unseen wall configurations. Performance gains scale with problem complexity: 23\% improvement for 16$\times$16 mazes, 34\% for 32$\times$32, and 55\% for 64$\times$64, demonstrating that as the space of possible maze structures grows, the value of adaptive policy selection over fixed heuristics increases proportionally.

Related papers

• Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's Role [5.210473713362396]
  We demonstrate that an AI agent can be surrendered to an autonomous agent in its entirety.<n>We adopt the autoresearch protocol, in which an AI agent edits a script, a fixedbudget experiment, and retains or discards the coding change according to an immutable metric.<n>In eighty-one twenty-six hours, the agent reached $99.5%$ of a converged minorization-maximization reference in one fixed-cost inference, at roughly $600times$ lower inference cost, closing $94%$ of the gap from its first working architecture.
  arXiv  Detail & Related papers  (2026-08-26T17:56:00Z)
• Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning [20.207338820226862]
  GRADE is a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning.<n>At $sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA.<n>On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks.
  arXiv  Detail & Related papers  (2026-07-12T16:58:21Z)
• What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests [39.407739937584104]
  AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change.<n>This distinction matters for search-based software engineering (SBSE), where techniques such as genetic improvement depend on mutation operators that reflect how code is actually transformed.<n>We classify 1,254 performance-relevant diff hunks from 216 of these PRs, spanning five agent systems.
  arXiv  Detail & Related papers  (2026-07-06T22:15:54Z)
• Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction [62.42945715963878]
  Repository-level vulnerability reproduction is a demanding software engineering (SE) task.<n>Recent LLM agents can often execute these steps when the approach is correct, yet they still fail by choosing the wrong strategy.<n>This paper argues that strategy, rather than the full action trajectory, is the right learning unit for such SE agents.
  arXiv  Detail & Related papers  (2026-07-02T06:27:27Z)
• Knowledge Reutilization in Meta-Reinforcement Learning [51.07319647819108]
  We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents.<n>We show that our framework reduces final-step tracking error by 94.75% -- 99.79% compared with recent state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T16:32:28Z)
• Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension [0.0]
  We show that modality-native routing in Agent-to-Agent networks improves task accuracy by 20 percentage points over text-bottleneck baselines.<n>We present MMA2A, an architecture layer atop A2A that inspects Agent Card capability declarations to route voice, image, and text parts in their native modality.
  arXiv  Detail & Related papers  (2026-04-14T02:44:50Z)
• Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning [0.0]
  PRISM is a framework that grounds reinforcement learning agents' decisions in discrete, causally validated concepts.<n> PRISM clusters each agent's encoder features into $K$ concepts via K-means.<n>Because concepts causally encode strategy, aligning them via optimal bipartite matching transfers strategic knowledge zero-shot.
  arXiv  Detail & Related papers  (2026-03-04T22:51:22Z)
• Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents [49.119608399413806]
  Large language models (LLMs) are increasingly deployed as autonomous agents for multi-turn decision-making tasks.<n>This paper introduces Cog, a framework that trains agents to dynamically adapt cognitive depth at each step.<n> Experiments on ALFWorld and ScienceWorld demonstrate that Cog achieves state-of-the-art performance with superior efficiency.
  arXiv  Detail & Related papers  (2026-02-13T06:52:09Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization [6.908972852063454]
  Temporal action localization requires both precise boundary detection and computational efficiency.<n>We address this through two complementary innovations: Boundary Distance Regression (BDR) and Adaptive Temporal Refinement (ATR)<n>On THUMOS14, our method achieves 56.5% mAP@0.7 with 151G FLOPs, using 36% fewer FLOPs than ActionFormer++ (55.7% mAP@0.7 at 235G)
  arXiv  Detail & Related papers  (2025-11-06T00:41:54Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving [76.5322280307861]
  StrategyLLM allows LLMs to perform inductive reasoning, deriving general strategies from specific task instances, and deductive reasoning, applying these general strategies to particular task examples, for constructing generalizable and consistent few-shot prompts. Experimental results demonstrate that StrategyLLM outperforms the competitive baseline CoT-SC that requires human-annotated solutions on 13 datasets across 4 challenging tasks without human involvement, including math reasoning (34.2% $rightarrow$ 38.8%), commonsense reasoning (70.3% $rightarrow$ 72.5%), algorithmic reasoning (73.7% $rightarrow$ 85.0
  arXiv  Detail & Related papers  (2023-11-15T09:18:09Z)
• Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition [63.67574523750839]
  We propose a generic reinforcement learning (RL) algorithm that performs better than baseline deep Q-learning algorithms in environments with multiple variably-valued niches. We show that agents trained this way can escape poor-but-attractive local optima to instead converge to harder-to-discover higher value strategies.
  arXiv  Detail & Related papers  (2023-02-02T16:00:19Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Influence-based Reinforcement Learning for Intrinsically-motivated Agents [0.0]
  We present an algorithmic framework of two reinforcement learning agents each with a different objective. We introduce a novel function approximation approach to assess the influence $F$ of a certain policy on others. Our method was evaluated on the suite of OpenAI gym tasks as well as cooperative and mixed scenarios.
  arXiv  Detail & Related papers  (2021-08-28T05:36:10Z)
• Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm [0.0]
  We develop a new framework for multi-agent collision avoidance problem. The framework combined traditional pathfinding algorithm and reinforcement learning. In our approach, the agents learn whether to be navigated or to take simple actions to avoid their partners.
  arXiv  Detail & Related papers  (2020-12-05T08:56:58Z)
• 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.