arXiv:2607. 18314v1 Announce Type: new Abstract: Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code.
arXiv:2606. 24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors.
Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors. The most effective defenses against this are (i) transparency through explainability and (ii) alignment via human feedback.
Large language model (LLM) agents are trained with reinforcement learning (RL) for complex decision-making tasks. However, most RL-trained agents remain episodic and cannot accumulate reusable knowled...
arXiv:2607. 05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making.
arXiv:2606. 06893v1 Announce Type: new Abstract: Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write.
arXiv:2608. 04934v1 Announce Type: cross Abstract: Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers.
arXiv:2607. 21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization.
The paper introduces SUN (Semantically UNified) Programs, typed executables that translate grounded relations into optimal control objectives, satisfaction predicates, and learning rewards. Using the Kuafu harness, a foundation model orchestrates scene preparation, verification, residual reinforcement learning, and data generation, repairing candidate programs and calibrating reward weights. Across nine multi‑stage manipulation tasks, Kuafu achieves an 82.03% success rate, outperforms learned baselines, generates demonstrations 10.57× faster than human teleoperation, and transfers zero‑shot to physical Franka and Kinova robots.
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Though effective, both remain bottlenecked by externally specified tasks and supervision signals, limiting the scalability and diversity of agent training.
arXiv:2511. 07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements.
arXiv:2602. 21534v3 Announce Type: replace Abstract: Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.
arXiv:2606. 29871v1 Announce Type: new Abstract: We present the AI Training Manager, a bounded LLM-based supervisory controller for adaptive machine learning training.