Recent studies on LLM agent scaling have highlighted the potential of Multi-Agent Debate (MAD) to enhance reasoning abilities. However, the critical aspect of role allocation strategies remains underexplored. In this study, we demonstrate that allocating roles with differing viewpoints to specific positions significantly impacts MAD's performance in reasoning tasks. Specifically, we find a novel role allocation strategy, "Truth Last", which can improve MAD performance by up to 22% in reasoning tasks. To address the issue of unknown truth in practical applications, we propose the Multi-Agent Debate Consistency (MADC) strategy, which systematically simulates and optimizes its core mechanisms. MADC incorporates path consistency to assess agreement among independent roles, simulating the role with the highest consistency score as the truth. We validated MADC across a range of LLMs (9 models), including the DeepSeek-R1 Distilled Models, on challenging reasoning tasks. MADC consistently demonstrated advanced performance, effectively overcoming MAD's performance bottlenecks and providing a crucial pathway for further improvements in LLM agent scaling.

Autonomous Feature Engineering (AFE) is critical for improving predictive performance on tabular data by relieving humans from manual feature crafting. However, traditional AFE lacks the semantic guidance needed to fully exploit domain knowledge. Although large language models (LLMs) can, in principle, emulate experts, existing approaches typically operate in an open code space that directly generates and rewrites entire features; without a compositional structural representation and invariant constraints, edits are coarse and non-local, making it hard to distill interpretable features with high information content and rich hierarchical structure.

Reinforcement Learning with Human Feedback (RLHF) has received significant attention for performing tasks without the need for costly manual reward design by aligning human preferences. It is crucial to consider diverse human feedback types and various learning methods in different environments. However, quantifying progress in RLHF with diverse feedback is challenging due to the lack of standardized annotation platforms and widely used unified benchmarks. To bridge this gap, we introduce **Uni-RLHF**, a comprehensive system implementation tailored for RLHF. It aims to provide a complete workflow from *real human feedback*, fostering progress in the development of practical problems. Uni-RLHF contains three packages: 1) a universal multi-feedback annotation platform, 2) large-scale crowdsourced feedback datasets, and 3) modular offline RLHF baseline implementations. Uni-RLHF develops a user-friendly annotation interface tailored to various feedback types, compatible with a wide range of mainstream RL environments. We then establish a systematic pipeline of crowdsourced annotations, resulting in large-scale annotated datasets comprising more than 15 million steps across 30 popular tasks. Through extensive experiments, the results in the collected datasets demonstrate competitive performance compared to those from well-designed manual rewards. We evaluate various design choices and offer insights into their strengths and potential areas of improvement. We wish to build valuable open-source platforms, datasets, and baselines to facilitate the development of more robust and reliable RLHF solutions based on realistic human feedback. The website is available at https://uni-rlhf.github.io/.

Decision Transformer (DT) is an innovative algorithm leveraging recent advances of the transformer architecture in reinforcement learning (RL). However, a notable limitation of DT is its reliance on recalling trajectories from datasets, losing the capability to seamlessly stitch sub-optimal trajectories together. In this work we introduce a general sequence modeling framework for studying sequential decision making through the lens of Hierarchical RL. At the time of making decisions, a high-level policy first proposes an ideal prompt for the current state, a low-level policy subsequently generates an action conditioned on the given prompt. We show DT emerges as a special case of this framework with certain choices of high-level and low-level policies, and discuss the potential failure of these choices. Inspired by these observations, we study how to jointly optimize the high-level and low-level policies to enable the stitching ability, which further leads to the development of new offline RL algorithms. Our empirical results clearly show that the proposed algorithms significantly surpass DT on several control and navigation benchmarks. We hope our contributions can inspire the integration of transformer architectures within the field of RL.

MinMax Multiple Travelling Salesman Problem (mTSP) is an important class of combinatorial optimization problems with many practical applications, of which the goal is to minimize the longest tour of all vehicles. Due to its high computational complexity, existing methods for solving this problem cannot obtain a solution of satisfactory quality with fast speed, especially when the scale of the problem is large. In this paper, we propose a learning-based method named SplitNet to transform the single TSP solutions into the MinMax mTSP solutions of the same instances. Specifically, we generate single TSP solution sequences and split them into mTSP subsequences using an attention-based model trained by reinforcement learning. We also design a decision region for the splitting policy, which significantly reduces the policy action space on instances of various scales and thus improves the generalization ability of SplitNet. The experimental results show that SplitNet generalizes well and outperforms existing learning-based baselines and Google OR-Tools on widely-used random datasets of different scales and public datasets with fast solving speed.

In this paper, we focus on the decision-making challenge in autonomous driving, a central and intricate problem influencing the safety and practicality of autonomous vehicles. We propose an innovative hierarchical imitation learning framework that effectively alleviates the complexity of learning in autonomous driving decision-making problems by decoupling decision-making tasks into sub-problems. Specifically, the decision-making process is divided into two levels of sub-problems: the upper level directs the vehicle's lane selection and qualitative speed management, while the lower level implements precise control of the driving speed and direction. We harness Transformer-based models for solving each sub-problem, enabling overall hierarchical framework to comprehend and navigate diverse and various road conditions, ultimately resulting in improved decision-making. Through an evaluation in several typical driving scenarios within the SMARTS autonomous driving simulation environment, our proposed hierarchical decision-making framework significantly outperforms end-to-end reinforcement learning algorithms and behavior cloning algorithm, achieving an average pass rate of over 90%. Our framework's effectiveness is substantiated by its commendable achievements at the NeurIPS 2022 Driving SMARTS competition, where it secures dual track championships.