SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents

• URL: http://arxiv.org/abs/2605.18636v1
• Date: Mon, 18 May 2026 16:43:32 GMT
• Title: SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
• Abstract summary: We present SPIKE, an adaptive dual controller framework for cost-efficient long-horizon game control.<n>Its Strategic Controller performs low-frequency global planning, failure analysis, and recovery, while its Reactive Controller handles fast local execution under a strict token budget.<n>An Event Trigger monitors visual change, task progress, repeated actions, and failure signals to decide when control should stay reactive or escalate to strategic reasoning.<n>This design reuses strategic proposals over multiple reactive steps, supports local override when plans become stale, and reserves expensive reasoning for moments where extra deliberation is useful.
• Score: 74.84742205422825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against reactive execution that can drift, repeat failures, and recover poorly. Our key idea is to reuse strategic reasoning across locally stable segments and reinvoke it at event boundaries. We present SPIKE, an adaptive dual controller framework for cost-efficient long-horizon game control. Its Strategic Controller performs low-frequency global planning, failure analysis, and recovery, while its Reactive Controller handles fast local execution under a strict token budget. An Event Trigger monitors visual change, task progress, repeated actions, and failure signals to decide when control should stay reactive or escalate to strategic reasoning. Hierarchical Memory separates short-term experience reuse in the State-Action Memory Bank (SA-MB) from structured evidence in the State Action Knowledge Graph (SA-KG), allowing each controller to retrieve the context it needs. This design reuses strategic proposals over multiple reactive steps, supports local override when plans become stale, and reserves expensive reasoning for moments where extra deliberation is useful. On the Lite-100 split of StarDojo, SPIKE improves Lite-100 success rate (SR) by 5.0 percentage points (38.5% relative) over the strongest Lite-100 baseline and Budgeted SR by 9.3 points (75.6% relative) over the strongest budgeted baseline. It also reduces token consumption by 54.9% and latency by 40.8%. Ablations show that event triggering, reactive override, and heterogeneous memory each contribute to success and recovery, supporting selective reasoning rather than reasoning at every step.

Related papers

• LePlanner: An Iterative Amortized Controller For World Models [0.0]
  We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor.<n>LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there.<n>It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task.
  arXiv  Detail & Related papers  (2026-09-12T10:01:21Z)
• LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning [4.794581688428893]
  EpicStar is a framework that enables agents to learn memory as policy to tackle long-horizon reasoning.<n>During inference, a dynamic gating mechanism determines whether to execute a retrieved action directly or to perform new reasoning.<n>It significantly outperforms baseline methods, achieving higher win rates while consuming an order of magnitude fewer tokens.
  arXiv  Detail & Related papers  (2026-08-12T22:17:24Z)
• When Replanning Becomes the Bottleneck: Budgeted Replanning for Embodied Agents [1.7674345486888505]
  We present BRACE, a controller that formulates replanning as a budgeted control loop.<n>We introduce E-RECAP, a cost-aware progressive token pruning method.<n>Across Meta Habitat, RoboFactory, and AirSim, BRACE with E-RECAP reduces replanning-call token counts by 62-92%.
  arXiv  Detail & Related papers  (2026-08-02T18:17:35Z)
• Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks [56.45762972211923]
  We present a proactive defense framework for securing LLMs against evolving multi-turn adversarial attacks.<n>It employs a cooperative multi-agent architecture in which specialized agents execute complementary defense strategies.<n>We present the EMRA dataset designed to simulate evolving strategies across multi-turn attacks.
  arXiv  Detail & Related papers  (2026-07-31T14:04:49Z)
• Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning [56.67877550139192]
  We conduct experiments across varying model scales, reasoning modes, and planning horizons.<n>We introduce a focused GVGAI benchmark consisting of three custom games with five difficulty levels to isolate spatial navigation.<n>Our results show that while larger models with an enabled thinking mode identify their positions more accurately, overall performance in coordinate matching remains limited for smaller models.
  arXiv  Detail & Related papers  (2026-07-22T12:10:45Z)
• Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning [27.851326399978394]
  Large language models improve final-answer accuracy through extended chain-of-thought reasoning.<n>Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces.<n>We propose Agentic Chain-of-Thought Steering (ACTS), which formulates reasoning steering as a Markov decision process.
  arXiv  Detail & Related papers  (2026-06-02T17:51:30Z)
• SeqRoute: Global Budget-Aware Sequential LLM Routing via Offline Reinforcement Learning [2.6853734738584047]
  SeqRoute is a framework that formulates multi-turn routing as a finite-horizon Markov Decision Process.<n>It learns delayed gratification to strategically preserve resources for high-stakes turns later in the session.<n>It reduces operational costs by 6.0-73.5% while maintaining or improving quality, and suppresses bankruptcy rates to under 1%.
  arXiv  Detail & Related papers  (2026-05-25T04:52:10Z)
• Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection [15.30405243180468]
  Long-horizon embodied manipulation tasks require persistent memory, adaptive task decomposition, and explicit recovery from execution failures.<n>Our framework explicitly separates high-level semantic reasoning from low-level motor execution.<n>A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory.<n>A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task.
  arXiv  Detail & Related papers  (2026-04-15T14:53:09Z)
• LightThinker++: From Reasoning Compression to Memory Management [61.2260619973687]
  Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces.<n>We propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations.<n>We evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management.
  arXiv  Detail & Related papers  (2026-04-04T10:46:09Z)
• M$^2$: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval [64.06936170117943]
  M$2$ is a training-free, memory-augmented framework designed to optimize context efficiency and decision-making.<n>Our approach incorporates a dual-tier memory mechanism that synergizes Dynamic Trajectory Summarization (Internal Memory) to compress verbose interaction history into concise state updates, and Insight Retrieval Augmentation (External Memory) to guide the agent with actionable guidelines retrieved from an offline insight bank.
  arXiv  Detail & Related papers  (2026-02-28T06:59:51Z)
• RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration [0.0]
  This paper proposes RLShield, a practical multi-agent RL pipeline for financial cyber defense.<n>We model the enterprise attack surface as a Markov decision process (MDP) where states summarize alerts, asset exposure, and service health, and actions represent real response steps.<n>Experiments show that RLShield reduces time-to-containment and residual exposure while keeping disruption within a fixed response budget.
  arXiv  Detail & Related papers  (2026-02-26T23:29:38Z)
• Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks [87.16809558673403]
  Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure.<n>We study a timing-only adversary that retimes existing spikes while preserving spike counts and amplitudes in event-driven SNNs.
  arXiv  Detail & Related papers  (2026-02-03T09:06:53Z)
• Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems [14.028345839891855]
  Retrieval-augmented generation (RAG) systems integrate document retrieval with large language models.<n>RAG introduces a new privacy risk: adversaries can issue carefully crafted queries to exfiltrate sensitive content gradually.<n>We introduce RAGCRAWLER, which builds a knowledge graph to represent revealed information, and plans queries in semantic space that target unretrieved regions.
  arXiv  Detail & Related papers  (2026-01-22T05:59:42Z)
• Controllable LLM Reasoning via Sparse Autoencoder-Based Steering [66.36947132041657]
  Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies.<n>Currently, reasoning strategies are autonomously selected by LRMs themselves.<n>Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs' hidden states.
  arXiv  Detail & Related papers  (2026-01-07T05:26:26Z)
• More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents [4.980051859336524]
  Coding agents operate in iterative loops (turns) to solve software engineering tasks.<n>They are becoming increasingly powerful, but their practical deployment is hindered by significant and unpredictable costs.<n>We show that a fixed-turn limit, specifically at the 75th percentile of the baseline, serves as a "sweet spot"<n>We then show that a fixed-turn strategy consistently outperforms fixed-limit approaches, achieving comparable or better solve rates while further reducing costs by an additional 12%-24% by intelligently allocating resources only to tasks that need them.
  arXiv  Detail & Related papers  (2025-10-19T10:32:18Z)

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.