Folgen

  • HazardWeaver: Scientific Route Selection for Hazard Analysis Agents

    HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
    Oct 7 2026
    Natural hazard analysis requires choosing scientific methods that are both appropriate for an event and executable with available data and tools, and those choices may need revising as evidence emerges. HazardWeaver frames this as state-dependent route selection. A Hazard Knowledge Compiler extracts applicability conditions, a Hazard Capability Graph checks input–output compatibility between executable capabilities, and an agent selects, runs, and revises workflows. Evaluated on a 141-instance benchmark spanning seven hazards and four multi-hazard interaction classes, it outperforms existing agents, especially with multiple valid routes. Authors: Wangshu Zhu, Xueqi Cheng, Liang Wu, Yushun Dong Paper: https://arxiv.org/abs/2610.03591v1
    Mehr anzeigen Weniger anzeigen
    3 Min.
  • When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game

    When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
    Oct 7 2026
    Reinforcement learning is increasingly applied to financial control, so this paper uses an analytically solved continuous-time broker–trader game to diagnose PPO. A PPO agent replaces the broker and sets trading speed. With no uninformed flow it approaches the reference action, but with stochastic flow, PPO–FFNN and PPO–LSTM remain inaccurate even though supervised learning shows the actors can represent the right action. Critics fail to rank nearby actions, and reward shaping doesn't help. Using the analytical policy as a starting point for adapting to changed costs does give improvement. Authors: Siu Tung Wong, Carlo Campajola Paper: https://arxiv.org/abs/2610.03598v1
    Mehr anzeigen Weniger anzeigen
    3 Min.
  • Low-Cost Video-Time Priors as a Strong Baseline for EEG-fNIRS Emotion Regression on Familiar Videos

    Low-Cost Video-Time Priors as a Strong Baseline for EEG-fNIRS Emotion Regression on Familiar Videos
    Oct 7 2026
    Continuous emotion regression estimates a viewer's moment-to-moment valence and arousal while watching video. For familiar videos, the authors find that a simple prior based on which video is playing and the time within it is a strong, low-cost baseline. In subject-held-out tests it came within 0.05 MAE of EEG-fNIRS fusion on the internal evaluation and within 0.32 on the external one. Gains from the brain signals were smaller and varied across participants and videos. Authors: Minghao Kong, Jiurun Chen, Ying Gao, Xiangbin Meng, Rongjie Wang Paper: https://arxiv.org/abs/2610.03618v1
    Mehr anzeigen Weniger anzeigen
    2 Min.
  • Depth as Time in One-Step Generative Models

    Depth as Time in One-Step Generative Models
    Oct 7 2026
    One-step generators compress multi-step diffusion into a single forward pass, raising the question of what happens to the denoising trajectory. The authors observe "depth as time": denoising unfolds across network layers and can be recovered by decoding intermediate layers with the model's own output head. The behavior depends on the training task; MeanFlow shows both denoising and renoising, while drifting models do not. Models showing it compress well, with a MeanFlow SiT-L/2 shrunk 16.6x into one time-conditioned block. Authors: Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun, Esin Tureci, Olga Russakovsky Paper: https://arxiv.org/abs/2610.03626v1
    Mehr anzeigen Weniger anzeigen
    2 Min.
  • NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents

    NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents
    Oct 7 2026
    Instrument design tests whether language-model agents can apply physics rather than recall it. NeutronGym is an executable environment for neutron instrument design: agents build instruments through validating tools, McStas ray-traces them, and a graded ladder scores syntax, runtime, structure, and science without an LLM judge. Seven frontier models reproduce at most 7 of 16 published instruments. RL on its reward lifts Qwen3-8B from 11% to 77% on held-out instances, surpassing an untrained Qwen3-32B. Authors: Lijie Ding, Changwoo Do Paper: https://arxiv.org/abs/2610.03631v1
    Mehr anzeigen Weniger anzeigen
    3 Min.
  • Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents

    Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents
    Oct 7 2026
    Terminal-using agents trained with reinforcement learning handle multi-step coding and debugging, but standard credit assignment ignores that later commands depend on earlier outputs, so training signals can land on irrelevant steps. DepGPO builds a command dependency graph from execution traces, traces backward from resources the task verifier inspects, and assigns credit to relevant writes and their supporting reads, redistributing trajectory advantages across steps. Experiments show better task performance and training stability on complex terminal tasks. Authors: Yu Li, Guangfeng Cai, Long-Fei Li, Shuo Han, Shengtian Yang, Han Luo, Kaibing Yang, Lei Feng Paper: https://arxiv.org/abs/2610.03634v1
    Mehr anzeigen Weniger anzeigen
    2 Min.
  • LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation

    LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
    Oct 7 2026
    Camera-controlled video models struggle with 3D inconsistency over long horizons: objects vanish or scene structure shifts as the camera moves. Post-training with a single scalar reward gives poor credit assignment for these local errors. LoGo blends global rewards, which preserve camera following and video quality, with spatially localized rewards that give fine-grained feedback. Tested on three base models, DL3DV, and the new TrajectoryBench for long, complex camera paths, it reduces object shifts, artifacts, and scene changes. Authors: Ziqi Ma, Shreya Sharma, Mohamed El Banani, Katja Schwarz, Chongjie Ye, Chao-Yuan Wu, Li Fei-Fei, Ben Mildenhall, Georgia Gkioxari, Justin Johnson, Gowthami Somepalli Paper: https://arxiv.org/abs/2610.03636v1
    Mehr anzeigen Weniger anzeigen
    3 Min.
  • Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System

    Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
    Oct 7 2026
    LLMs are increasingly used in legal work, yet their reliability outside the United States is poorly documented. This expert-validated benchmark has 1,042 items across ten areas of law and three formats, and was used to test 15 models. Closed-question accuracy reaches 0.905, but free-text correctness never exceeds 0.45, and only about half of cited norms are correct. Models often sound responsive while being wrong, which is risky for non-experts. Authors: Rubén Manrique, Michelle Castellanos, Jorge Morales, Juan David Gutiérrez, Antonio Barreto Rozo, Joaquín Vélez Navarro Paper: https://arxiv.org/abs/2610.03639v1
    Mehr anzeigen Weniger anzeigen
    2 Min.