EnvHarness: Awakening Static Worlds for Agent Learning

• URL: http://arxiv.org/abs/2608.19880v1
• Date: Thu, 20 Aug 2026 10:42:06 GMT
• Title: EnvHarness: Awakening Static Worlds for Agent Learning
• Abstract summary: Environment Harness wraps a static environment to reshape its behavior without modifying the underlying logic.<n>EnvHarness applies across diverse domains while ensuring every reshaped environment retains its original verifier.<n>EnvRigger treats the target policy as a black box, observing its execution trajectories to synthesize EnvHarness components targeting diagnosed flaws.
• Score: 58.54600450547412
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive or unreliable verifiers, and still produce static environments. To alleviate the engineering burden of rebuilding environments from scratch, we propose Environment Harness (EnvHarness), a programmable layer of plug-in components that wraps a static environment to reshape its behavior without modifying the underlying logic. Operating through standard interfaces, EnvHarness applies across diverse domains while ensuring every reshaped environment retains its original verifier. To automate this process, we introduce EnvRigger, which treats the target policy as a black box, observing its execution trajectories to synthesize EnvHarness components targeting diagnosed flaws, and validating them via fresh rollouts. Across five benchmarks in four domains, EnvHarness outperforms both original environments and domain-specific environment generation pipelines, achieving up to a 9.0-point improvement on held-out instances with 9.8% fewer execution steps. Furthermore, EnvHarness provides a superior optimization signal for reinforcement learning, enabling continuous, targeted co-evolution of the policy and its environment.

Related papers

• SPADE: Self-Play in Adaptive Synthetic Executable Environments [110.80471334001574]
  We introduce SPADE, a self-play RL framework in which a single LLM plays two roles.<n>The Environment Designer writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface.<n>We find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory.
  arXiv  Detail & Related papers  (2026-08-19T17:58:56Z)
• OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution [71.06848799741152]
  AI agents operate in persistent environments where early state changes can influence decisions far into the future.<n>Current safety benchmarks often fail to capture cumulative risks because they focus on short, static tasks.<n>We introduce OpenART, an open-ended arena for scalable agent red teaming through environment evolution.
  arXiv  Detail & Related papers  (2026-08-01T13:51:55Z)
• EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation [16.36266898493489]
  A promising direction is to replace manually crafted environments with LLM-simulated counterparts.<n>This paradigm hinges on an unexamined core assumption: LLMs can accurately simulate environmental feedback.<n>In practice, LLM-simulated environments suffer from hallucinations, logical inconsistencies, and silent state drift failures.
  arXiv  Detail & Related papers  (2026-05-08T05:08:16Z)
• Computer Use at the Edge of the Statistical Precipice [19.604476051265852]
  We show that a 1MB replay script that blindly executes a recorded action sequence outperforms frontier models on prominent static benchmarks.<n>We trace failures to two root causes: non-principled environment design and non-principled evaluation methodology.
  arXiv  Detail & Related papers  (2026-05-07T22:43:43Z)
• Robust Cross-Domain WiFi Fall Detection via Physics-Driven Attention-Enhanced Transformers [64.35403680946182]
  Device-free fall detection utilizing WiFi Channel State Information (CSI) has emerged as a promising solution for elderly health monitoring.<n>Existing deep learning approaches suffer from severe performance degradation when deployed in unseen environments.<n>We propose a robust, domain-general framework featuring a novel Attention-Enhanced CNN-Transformer hybrid architecture.
  arXiv  Detail & Related papers  (2026-04-23T03:28:12Z)
• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• Towards Adaptive Environment Generation for Training Embodied Agents [6.22572530511425]
  Embodied agents struggle to generalize to new environments.<n>Most current approaches to generating these training environments follow an open-loop paradigm.<n>We present a proof-of-concept for closed-loop environment generation that adapts difficulty to the agent's current capabilities.
  arXiv  Detail & Related papers  (2026-02-06T03:50:46Z)
• EnvGuard: Guaranteeing Environment-Centric Safety and Security Properties in Web of Things [5.523305571662793]
  Web of Things (WoT) technology promotes diverse WoT applications to automatically sense and regulate the environment. Existing work on violation identification primarily focuses on the analysis of automated applications. We introduce EnvGuard, an environment-centric approach for property customizing, violation identification and resolution execution in WoT environment.
  arXiv  Detail & Related papers  (2023-12-06T09:15:52Z)
• Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design [121.73425076217471]
  We propose Unsupervised Environment Design (UED), where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED) Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.
  arXiv  Detail & Related papers  (2020-12-03T17:37:01Z)

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.