Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery

As the significance of understanding the cause-and-effect relationships among variables increases in the development of modern systems and algorithms, learning causality from observational data has become a preferred and efficient approach over conducting randomized control trials. However, purely observational data could be insufficient to reconstruct the true causal graph. Consequently, many researchers tried to utilise some form of prior knowledge to improve causal discovery process. In this context, the impressive capabilities of large language models (LLMs) have emerged as a promising alternative to the costly acquisition of prior expert knowledge. In this work, we further explore the potential of using LLMs to enhance causal discovery approaches, particularly focusing on score-based methods, and we propose a general framework to utilise the capacity of not only one but multiple LLMs to augment the discovery process.

Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens

Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by using previously generated tokens as input to predict the next one. Marginal differences in predictions at each step can cascade over successive steps, resulting in different distributions from what the models were trained for and potentially leading to unpredictable behavior. This paper proposes two simple approaches based on model own generation to address this discrepancy between the training and inference time. Our first approach is Batch-Scheduled Sampling, where, during training, we stochastically choose between the ground-truth token from the dataset and the model's own generated token as input to predict the next token. This is done in an offline manner, modifying the context window by interleaving ground-truth tokens with those generated by the model. Our second approach is Reference-Answer-based Correction, where we explicitly incorporate a self-correction capability into the model during training. This enables the model to effectively self-correct the gaps between the generated sequences and the ground truth data without relying on an external oracle model. By incorporating our proposed strategies during training, we have observed an overall improvement in performance compared to baseline methods, as demonstrated by our extensive experiments using summarization, general question-answering, and math question-answering tasks.

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Autonomy via agents using large language models (LLMs) for personalized, standardized tasks boosts human efficiency. Automating web tasks (like booking hotels within a budget) is increasingly sought after. Fulfilling practical needs, the web agent also serves as an important proof-of-concept example for various agent grounding scenarios, with its success promising advancements in many future applications. Prior research often handcrafts web agent strategies (e.g., prompting templates, multi-agent systems, search methods, etc.) and the corresponding in-context examples, which may not generalize well across all real-world scenarios. On the other hand, there has been limited study on the misalignment between a web agent's observation/action representation and the pre-training data of the LLM it's based on. This discrepancy is especially notable when LLMs are primarily trained for language completion rather than tasks involving embodied navigation actions and symbolic web elements. Our study enhances an LLM-based web agent by simply refining its observation and action space to better align with the LLM's capabilities. This approach enables our base agent to significantly outperform previous methods on a wide variety of web tasks. Specifically, on WebArena, a benchmark featuring general-purpose web interaction tasks, our agent AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively, and boosts the success rate by 26.6 points (+161%) over similar plain web agents with its observation and action space alignment. We achieve this without using in-context examples, new agent roles, online feedback or search strategies. AgentOccam's simple design highlights LLMs' impressive zero-shot performance on web tasks, and underlines the critical role of carefully tuning observation and action spaces for LLM-based agents.

Causality-Aware Transformer Networks for Robotic Navigation

Recent advances in machine learning algorithms have garnered growing interest in developing versatile Embodied AI systems. However, current research in this domain reveals opportunities for improvement. First, the direct adoption of RNNs and Transformers often overlooks the specific differences between Embodied AI and traditional sequential data modelling, potentially limiting its performance in Embodied AI tasks. Second, the reliance on task-specific configurations, such as pre-trained modules and dataset-specific logic, compromises the generalizability of these methods. We address these constraints by initially exploring the unique differences between Embodied AI tasks and other sequential data tasks through the lens of Causality, presenting a causal framework to elucidate the inadequacies of conventional sequential methods for Embodied AI. By leveraging this causal perspective, we propose Causality-Aware Transformer (CAT) Networks for Navigation, featuring a Causal Understanding Module to enhance the models's Environmental Understanding capability. Meanwhile, our method is devoid of task-specific inductive biases and can be trained in an End-to-End manner, which enhances the method's generalizability across various contexts. Empirical evaluations demonstrate that our methodology consistently surpasses benchmark performances across a spectrum of settings, tasks and simulation environments. Extensive ablation studies reveal that the performance gains can be attributed to the Causal Understanding Module, which demonstrates effectiveness and efficiency in both Reinforcement Learning and Supervised Learning settings.

EXTRACT: Efficient Policy Learning by Extracting Transferrable Robot Skills from Offline Data

Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL agents that can act over useful, temporally extended skills rather than low-level actions can learn new tasks more easily. Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to transfer during downstream RL. Our approach, EXTRACT, instead utilizes pre-trained vision language models to extract a discrete set of semantically meaningful skills from offline data, each of which is parameterized by continuous arguments, without human supervision. This skill parameterization allows robots to learn new tasks by only needing to learn when to select a specific skill and how to modify its arguments for the specific task. We demonstrate through experiments in sparse-reward, image-based, robot manipulation environments that EXTRACT can more quickly learn new tasks than prior works, with major gains in sample efficiency and performance over prior skill-based RL. Website at https://www.jessezhang.net/projects/extract/.

Learning the Target Network in Function Space

We focus on the task of learning the value function in the reinforcement learning (RL) setting. This task is often solved by updating a pair of online and target networks while ensuring that the parameters of these two networks are equivalent. We propose Lookahead-Replicate (LR), a new value-function approximation algorithm that is agnostic to this parameter-space equivalence. Instead, the LR algorithm is designed to maintain an equivalence between the two networks in the function space. This value-based equivalence is obtained by employing a new target-network update. We show that LR leads to a convergent behavior in learning the value function. We also present empirical results demonstrating that LR-based target-network updates significantly improve deep RL on the Atari benchmark.

Modeling Pedestrian Intrinsic Uncertainty for Multimodal Stochastic Trajectory Prediction via Energy Plan Denoising

Pedestrian trajectory prediction plays a pivotal role in the realms of autonomous driving and smart cities. Despite extensive prior research employing sequence and generative models, the unpredictable nature of pedestrians, influenced by their social interactions and individual preferences, presents challenges marked by uncertainty and multimodality. In response, we propose the Energy Plan Denoising (EPD) model for stochastic trajectory prediction. EPD initially provides a coarse estimation of the distribution of future trajectories, termed the Plan, utilizing the Langevin Energy Model. Subsequently, it refines this estimation through denoising via the Probabilistic Diffusion Model. By initiating denoising with the Plan, EPD effectively reduces the need for iterative steps, thereby enhancing efficiency. Furthermore, EPD differs from conventional approaches by modeling the distribution of trajectories instead of individual trajectories. This allows for the explicit modeling of pedestrian intrinsic uncertainties and eliminates the need for multiple denoising operations. A single denoising operation produces a distribution from which multiple samples can be drawn, significantly enhancing efficiency. Moreover, EPD's fine-tuning of the Plan contributes to improved model performance. We validate EPD on two publicly available datasets, where it achieves state-of-the-art results. Additionally, ablation experiments underscore the contributions of individual modules, affirming the efficacy of the proposed approach.

Multi-agent Traffic Prediction via Denoised Endpoint Distribution

The exploration of high-speed movement by robots or road traffic agents is crucial for autonomous driving and navigation. Trajectory prediction at high speeds requires considering historical features and interactions with surrounding entities, a complexity not as pronounced in lower-speed environments. Prior methods have assessed the spatio-temporal dynamics of agents but often neglected intrinsic intent and uncertainty, thereby limiting their effectiveness. We present the Denoised Endpoint Distribution model for trajectory prediction, which distinctively models agents' spatio-temporal features alongside their intrinsic intentions and uncertainties. By employing Diffusion and Transformer models to focus on agent endpoints rather than entire trajectories, our approach significantly reduces model complexity and enhances performance through endpoint information. Our experiments on open datasets, coupled with comparison and ablation studies, demonstrate our model's efficacy and the importance of its components. This approach advances trajectory prediction in high-speed scenarios and lays groundwork for future developments.

Cognitive Bias in High-Stakes Decision-Making with LLMs

Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. However, given their training on human (created) data, LLMs can inherit both societal biases against protected groups, as well as be subject to cognitive bias. Such human-like bias can impede fair and explainable decisions made with LLM assistance. Our work introduces BiasBuster, a framework designed to uncover, evaluate, and mitigate cognitive bias in LLMs, particularly in high-stakes decision-making tasks. Inspired by prior research in psychology and cognitive sciences, we develop a dataset containing 16,800 prompts to evaluate different cognitive biases (e.g., prompt-induced, sequential, inherent). We test various bias mitigation strategies, amidst proposing a novel method using LLMs to debias their own prompts. Our analysis provides a comprehensive picture on the presence and effects of cognitive bias across different commercial and open-source models. We demonstrate that our self-help debiasing effectively mitigate cognitive bias without having to manually craft examples for each bias type.

InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment

Do current large language models (LLMs) better solve graph reasoning and generation tasks with parameter updates? In this paper, we propose InstructGraph, a framework that empowers LLMs with the abilities of graph reasoning and generation by instruction tuning and preference alignment. Specifically, we first propose a structured format verbalizer to unify all graph data into a universal code-like format, which can simply represent the graph without any external graph-specific encoders. Furthermore, a graph instruction tuning stage is introduced to guide LLMs in solving graph reasoning and generation tasks. Finally, we identify potential hallucination problems in graph tasks and sample negative instances for preference alignment, the target of which is to enhance the output's reliability of the model. Extensive experiments across multiple graph-centric tasks exhibit that InstructGraph can achieve the best performance and outperform GPT-4 and LLaMA2 by more than 13\% and 38\%, respectively.