RL benchmark tailored for embodied pixel-based RL.

In the methods, they stick to a single static memory construction policy, which is prone to failing in the long task sequence.

We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.

The increasing labor costs in agriculture have accelerated the adoption of multi-robot systems for orchard harvesting. However, efficiently coordinating these systems is challenging due to the complex interplay between makespan and energy consumption, particularly under practical constraints like load-dependent speed variations and battery limitations. This paper defines the multi-objective agricultural multi-electrical-robot task allocation (AMERTA) problem, which systematically incorporates these often-overlooked real-world constraints. To address this problem, we propose a hybrid hierarchical route reconstruction algorithm (HRRA) that integrates several innovative mechanisms, including a hierarchical encoding structure, a dual-phase initialization method, task sequence optimizers, and specialized route reconstruction operators. Extensive experiments on 45 test instances demonstrate HRRA's superior performance against seven state-of-the-art algorithms. Statistical analysis, including the Wilcoxon signed-rank and Friedman tests, empirically validates HRRA's competitiveness and its unique ability to explore previously inaccessible regions of the solution space. In general, this research contributes to the theoretical understanding of multi-robot coordination by offering a novel problem formulation and an effective algorithm, thereby also providing practical insights for agricultural automation.

In this article, we address the problem of collaborative task assignment, sequencing, and multi-agent pathfinding (TSPF), where a team of agents must visit a set of task locations without collisions while minimizing flowtime. TSPF incorporates agent-task compatibility constraints and ensures that all tasks are completed. We propose a Conflict-Based Search with Task Sequencing (CBS-TS), an optimal and complete algorithm that alternates between finding new task sequences and resolving conflicts in the paths of current sequences. CBS-TS uses a mixed-integer linear program (MILP) to optimize task sequencing and employs Conflict-Based Search (CBS) with Multi-Label A* (MLA*) for collision-free path planning within a search forest. By invoking MILP for the next-best sequence only when needed, CBS-TS efficiently limits the search space, enhancing computational efficiency while maintaining optimality. We compare the performance of our CBS-TS against Conflict-based Steiner Search (CBSS), a baseline method that, with minor modifications, can address the TSPF problem. Experimental results demonstrate that CBS-TS outperforms CBSS in most testing scenarios, achieving higher success rates and consistently optimal solutions, whereas CBSS achieves near-optimal solutions in some cases. The supplementary video is available at https://youtu.be/QT8BYgvefmU.

RL benchmark tailored for embodied pixel-based RL.

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of task-specific prompts, which introduces two major challenges: (1) severe performance degradation on earlier tasks under task-agnostic inference, and (2) limited scalability due to prompt memory accumulation as task sequences grow. In this paper, we present GRID, a unified framework designed to address these challenges. GRID incorporates a decoding mechanism that enhances backward transfer by leveraging representative inputs, automatic task identification, and constrained decoding. Furthermore, it employs a gradient-guided prompt selection strategy to compress less informative prompts into a single aggregated representation, ensuring scalable and memory-efficient continual learning. Extensive experiments on long-sequence and negative transfer benchmarks show that GRID improves average accuracy and backward transfer, achieves competitive forward transfer, and substantially reduces prompt memory usage.

Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms, with environment availability strongly impacting research. One particularly underexplored intersection is continual learning (CL) in cooperative multi-agent settings. To remedy this, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark tailored for continual multi-agent reinforcement learning (CMARL). Existing CL benchmarks run environments on the CPU, leading to computational bottlenecks and limiting the length of task sequences. MEAL leverages JAX for GPU acceleration, enabling continual learning across sequences of 100 tasks on a standard desktop PC in a few hours. We show that naively combining popular CL and MARL methods yields strong performance on simple environments, but fails to scale to more complex settings requiring sustained coordination and adaptation. Our ablation study identifies architectural and algorithmic features critical for CMARL on MEAL.