STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics

• URL: http://arxiv.org/abs/2605.18548v1
• Date: Mon, 18 May 2026 15:27:52 GMT
• Title: STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
• Abstract summary: Large language models (LLMs) in real-world agentic applications must be capable of replanning and adapting when mid- disruptions invalidate their prior decisions.<n>We introduce STT-Arena, a benchmark for high-quality interactive tasks spanning nine-Stemporal conflict types and four solvability levels.
• Score: 22.402787444770908
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a realistic, executable environment equipped with injected spatio-temporal triggers that can abruptly invalidate an ongoing plan, forcing the model to detect the state shift and construct a revised execution strategy. Extensive evaluation of frontier LLMs reveals that even the SOTA proprietary models, including Claude-4.6-Opus, achieves less than 40\% overall accuracies, highlighting the fundamental difficulty of spatio-temporal dynamic reasoning. Systematic analysis of failure trajectories uncovers three recurring error modes of existing models: Stale-State Execution, Misdiagnosis of Dynamic Triggers, and Missing Post-Adaptation Verification. Guided by these findings, we propose an iterative trajectory refinement technique that eliminates these failure patterns from training data, and combine it with online RL to produce STT-Agent-4B which outperforms frontier LLMs on STT-Arena.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning [5.5818653283217055]
  Multi-Robot Motion Planning in continuous environments is challenging due to the growth of the joint trajectory space and the difficulty of enforcing dynamic feasibility and hard safety constraints.<n>Recent approaches recast trajectory planning as probabilistic inference, sampling from a posterior over trajectories using diffusion models whose score functions are learned from demonstration data.<n>We introduce Model-Based Diffusion Optimal Control (MDOC), a model-based diffusion planner that efficiently produces dynamically feasible trajectories without relying on data.
  arXiv  Detail & Related papers  (2026-07-14T06:54:03Z)
• SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors [48.60897189520386]
  We introduce the JEPA-style model for real-time quadrotor control.<n>We combine a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state.<n>To reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation.
  arXiv  Detail & Related papers  (2026-06-22T15:00:59Z)
• Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL [0.8546394944138487]
  We formalize text-based world modeling as a steerable transition-dynamics problem decomposed into initial state.<n>We curate 239,403 grounded state-action trajectories spanning nine open-source environments and twelve frontier model families.<n>We introduce a plug-and-play GRPO training framework with deterministic state checks, and perform zero-shot transfer ablations on three OOD environments.
  arXiv  Detail & Related papers  (2026-05-07T00:40:32Z)
• LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning [90.86828952599147]
  We present LaST-R1, a novel reinforcement learning framework designed to harness "latent reasoning-before-acting" policies.<n>LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark.<n>In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach.
  arXiv  Detail & Related papers  (2026-04-30T17:59:52Z)
• Temporally Decoupled Diffusion Planning for Autonomous Driving [6.701508758642954]
  Motion planning in dynamic urban environments requires balancing immediate safety with long-term goals.<n>We propose Temporally Decoupled Diffusion Model (TDDM), which reformulates trajectory generation via a noise-as-mask paradigm.<n>By partitioning trajectories into segments with independent noise levels, we implicitly treat high noise as information voids and weak noise as contextual cues.<n>This compels the model to corrupted near-term states by leveraging internal correlations with better-preserved temporal contexts.
  arXiv  Detail & Related papers  (2026-03-26T14:04:15Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation [72.78362530982109]
  ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, is a framework that decouples exploration from commitment.<n>We show that naive LLM-based simulators struggle to capture rare but high-impact failure modes.<n>We introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions.
  arXiv  Detail & Related papers  (2026-02-02T06:33:22Z)
• Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG [35.96258615258145]
  We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty.<n>ETC consistently outperforms strong baselines while reducing retrieval frequency.<n>It is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines.
  arXiv  Detail & Related papers  (2025-11-13T05:28:02Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• Real-Time Anomaly Detection and Reactive Planning with Large Language Models [18.57162998677491]
  Foundation models, e.g., large language models (LLMs), trained on internet-scale data possess zero-shot capabilities. We present a two-stage reasoning framework that incorporates the judgement regarding potential anomalies into a safe control framework. This enables our monitor to improve the trustworthiness of dynamic robotic systems, such as quadrotors or autonomous vehicles.
  arXiv  Detail & Related papers  (2024-07-11T17:59:22Z)

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.