The paper introduces GARDEN, a framework that uses large language models to autonomously design a single reward program for cooperative multi‑agent reinforcement learning tasks. By navigating evidence from environment code, training logs, and agent behavior, the reward is tested and finalized without altering the learning algorithm. Experiments on Overcooked and SMAX benchmarks show that the autonomously engineered reward improves task returns by up to 58.2% and win rates by up to 89.9% compared to default rewards, outperforming prior methods.
arXiv:2606.03963v4 Announce Type: replace-cross Abstract: Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual re...
arXiv:2610.15691v1 Announce Type: new Abstract: Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new...
UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.
arXiv:2502. 00345v2 Announce Type: replace-cross Abstract: The critical role of division of labor (DOL) in enhancing cooperation is well-recognized in real-world applications.
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.
arXiv:2606. 01672v1 Announce Type: new Abstract: Reinforcement learning has enabled the acquisition of impressive robotic skills, but typically requires hand-crafted reward functions that are slow to design and difficult to align with human intentions.
arXiv:2511. 02304v2 Announce Type: replace-cross Abstract: We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution.
arXiv:2604.00055v2 Announce Type: replace-cross Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilit...
arXiv:2607. 25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy.
AgentRM proposes a generalizable reward model to guide LLM-based agents during test-time search, outperforming direct policy fine-tuning. Three reward modeling strategies—explicit, implicit, and LLM-as-a-judge—are explored, and AgentRM improves base policy performance by an average of 8.8 points across nine tasks, surpassing top general agents by 4.0 points. It also shows strong weak-to-strong generalization and can boost specialized agents, with plans to release code for further research.
JoyInside‑VLM‑Agent is a ReAct‑style multimodal agent that learns product‑conditioned policies for embodied robots and smart hardware. It uses a closed‑loop sandbox to generate interaction trajectories, supervised fine‑tuning, multi‑teacher on‑policy distillation, and reinforcement learning with DPER to align token‑level evidence and rewards. The agent achieves a BFCL v4 overall score of 77.44, surpassing baselines on JoyInside‑Devices and JoyInside‑Robotics, and demonstrates visually grounded search, replanning, and failure reporting in two real‑world quadruped case studies.
arXiv:2606. 03963v2 Announce Type: replace-cross Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks.