Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities; however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies-areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse set of challenging games. Our benchmark incorporates a range of existing reinforcement learning environments with varying levels of difficulty, including tasks that are solvable by non-expert humans in seconds to extremely challenging ones that may take years to master (e.g., the NetHack Learning Environment). We devise fine-grained metrics to measure performance and conduct an extensive evaluation of several popular open-source and closed-source LLMs and VLMs. Our findings indicate that while current models achieve partial success in the easier games, they struggle significantly with more challenging tasks. Notably, we observe severe deficiencies in vision-based decision-making, as models perform worse when visual representations of the environments are provided. We release BALROG as an open and user-friendly benchmark to facilitate future research and development in the agentic community.

Software engineers mainly write code by editing existing programs. In contrast, large language models (LLMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of open-sourced edit data. While high-quality instruction data for code synthesis is already scarce, high-quality edit data is even scarcer. To fill this gap, we develop a synthetic data generation algorithm called LintSeq. This algorithm refactors existing code into a sequence of code edits by using a linter to procedurally sample across the error-free insertions that can be used to sequentially write programs. It outputs edit sequences as text strings consisting of consecutive program diffs. To test LintSeq, we use it to refactor a dataset of instruction + program pairs into instruction + program-diff-sequence tuples. Then, we instruction finetune a series of smaller LLMs ranging from 2.6B to 14B parameters on both the re-factored and original versions of this dataset, comparing zero-shot performance on code synthesis benchmarks. We show that during repeated sampling, edit sequence finetuned models produce more diverse programs than baselines. This results in better inference-time scaling for benchmark coverage as a function of samples, i.e. the fraction of problems "pass@k" solved by any attempt given "k" tries. For example, on HumanEval pass@50, small LLMs finetuned on synthetic edit sequences are competitive with GPT-4 and outperform models finetuned on the baseline dataset by +20% (+/-3%) in absolute score. Finally, we also pretrain our own tiny LMs for code understanding. We show that finetuning tiny models on synthetic code edits results in state-of-the-art code synthesis for the on-device model class. Our 150M parameter edit sequence LM matches or outperforms code models with twice as many parameters, both with and without repeated sampling, including Codex and AlphaCode.

Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than embedding-based models (dual-encoders) at estimating query-item relevance. Existing approaches perform k-NN search with CE by approximating the CE similarity with a vector embedding space fit either with dual-encoders (DE) or CUR matrix factorization. DE-based retrieve-and-rerank approaches suffer from poor recall on new domains and the retrieval with DE is decoupled from the CE. While CUR-based approaches can be more accurate than the DE-based approach, they require a prohibitively large number of CE calls to compute item embeddings, thus making it impractical for deployment at scale. In this paper, we address these shortcomings with our proposed sparse-matrix factorization based method that efficiently computes latent query and item embeddings to approximate CE scores and performs k-NN search with the approximate CE similarity. We compute item embeddings offline by factorizing a sparse matrix containing query-item CE scores for a set of train queries. Our method produces a high-quality approximation while requiring only a fraction of CE calls as compared to CUR-based methods, and allows for leveraging DE to initialize the embedding space while avoiding compute- and resource-intensive finetuning of DE via distillation. At test time, the item embeddings remain fixed and retrieval occurs over rounds, alternating between a) estimating the test query embedding by minimizing error in approximating CE scores of items retrieved thus far, and b) using the updated test query embedding for retrieving more items. Our k-NN search method improves recall by up to 5% (k=1) and 54% (k=100) over DE-based approaches. Additionally, our indexing approach achieves a speedup of up to 100x over CUR-based and 5x over DE distillation methods, while matching or improving k-NN search recall over baselines.

Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, which coupled with history, leads to prohibitively large textual prompts. As a result, prior work in LM agents is limited to restricted domains with either small observation size or minimal needs for interaction history. In this paper, we introduce a simple and highly effective solution to these issues. We exploit the fact that consecutive text observations have high similarity and propose to compress them via the Unix diff command. We demonstrate our approach in NetHack, a complex rogue-like video game, that requires long-horizon reasoning for decision-making and is far from solved, particularly for neural agents. Diff history offers an average of 4x increase in the length of the text-based interaction history available to the LM. This observational compression along with the benefits of abstraction yields a 7x improvement in game score on held-out environment instances over state-of-the-art baselines. It also outperforms prior agents that use visual observations by over 40%.

Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density functions. This interpretation has motivated classifier-based and classifier-free guidance as methods for post-hoc control of diffusion models. In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and guidance. In particular, we investigate why certain types of composition fail using current techniques and present a number of solutions. We conclude that the sampler (not the model) is responsible for this failure and propose new samplers, inspired by MCMC, which enable successful compositional generation. Further, we propose an energy-based parameterization of diffusion models which enables the use of new compositional operators and more sophisticated, Metropolis-corrected samplers. Intriguingly we find these samplers lead to notable improvements in compositional generation across a wide set of problems such as classifier-guided ImageNet modeling and compositional text-to-image generation.

Neural policy learning methods have achieved remarkable results in various control problems, ranging from Atari games to simulated locomotion. However, these methods struggle in long-horizon tasks, especially in open-ended environments with multi-modal observations, such as the popular dungeon-crawler game, NetHack. Intriguingly, the NeurIPS 2021 NetHack Challenge revealed that symbolic agents outperformed neural approaches by over four times in median game score. In this paper, we delve into the reasons behind this performance gap and present an extensive study on neural policy learning for NetHack. To conduct this study, we analyze the winning symbolic agent, extending its codebase to track internal strategy selection in order to generate one of the largest available demonstration datasets. Utilizing this dataset, we examine (i) the advantages of an action hierarchy; (ii) enhancements in neural architecture; and (iii) the integration of reinforcement learning with imitation learning. Our investigations produce a state-of-the-art neural agent that surpasses previous fully neural policies by 127% in offline settings and 25% in online settings on median game score. However, we also demonstrate that mere scaling is insufficient to bridge the performance gap with the best symbolic models or even the top human players.

Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge has been to find the right space of sub-goals over which to instantiate a hierarchy. We present a novel approach where we use data from humans solving these tasks to softly supervise the goal space for a set of long range tasks in a 3D embodied environment. In particular, we use unconstrained natural language to parameterize this space. This has two advantages: first, it is easy to generate this data from naive human participants; second, it is flexible enough to represent a vast range of sub-goals in human-relevant tasks. Our approach outperforms agents that clone expert behavior on these tasks, as well as HRL from scratch without this supervised sub-goal space. Our work presents a novel approach to combining human expert supervision with the benefits and flexibility of reinforcement learning.

Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the way for the resource-efficient deployment of such models in practice. Inspired by our theoretical analysis of the teacher-student generalization gap for IR models, we propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. Unlike existing teacher score-based distillation methods, our proposed approach employs embedding matching tasks to provide a stronger signal to align the representations of the teacher and student models. In addition, it utilizes query generation to explore the data manifold to reduce the discrepancies between the student and the teacher where training data is sparse. Furthermore, our analysis also motivates novel asymmetric architectures for student models which realizes better embedding alignment without increasing online inference cost. On standard benchmarks like MSMARCO, we show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.

Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To address this challenge, we propose using pretrained vision-language models (VLMs) to supervise embodied agents. We combine ideas from model distillation and hindsight experience replay (HER), using a VLM to retroactively generate language describing the agent's behavior. Simple prompting allows us to control the supervision signal, teaching an agent to interact with novel objects based on their names (e.g., planes) or their features (e.g., colors) in a 3D rendered environment. Fewshot prompting lets us teach abstract category membership, including pre-existing categories (food vs toys) and ad-hoc ones (arbitrary preferences over objects). Our work outlines a new and effective way to use internet-scale VLMs, repurposing the generic language grounding acquired by such models to teach task-relevant groundings to embodied agents.

Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory capability, altering the agent's intrinsic motivation (i.e. exploration) or its worldview (i.e. knowledge representation). Many of these components could be learned from offline data. In this work, we follow the hypothesis that exploration and representation learning can be improved by separately learning two different models from a single offline dataset. We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward separately from a single collection of human demonstrations can significantly improve the sample efficiency on the challenging NetHack benchmark. We also ablate various components of our experimental setting and highlight crucial insights.