Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors encountered in the training data. These reactive agents are insufficient for long-horizon complex tasks. To address this limitation, we propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience (e.g., natural language and egocentric vision). We show that our deliberative agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark. Moreover, the underlying reasoning and planning processes, together with our modular framework, offer impressive transparency and explainability to the behaviors of the agent. This enables an in-depth understanding of the agent's capabilities, which shed light on challenges and opportunities for future embodied agents for instruction following. The code is available at https://github.com/sled-group/DANLI.

In many real-world auctions, a bidder does not know her exact value for an item, but can perform a costly deliberation to reduce her uncertainty. Relatively little is known about such deliberative environments, which are fundamentally different from classical auction environments. In this paper, we propose a new approach that allows us to leverage classical revenue-maximization results in deliberative environments. In particular, we use Myerson (1981) to construct the first non-trivial (i.e., dependent on deliberation costs) upper bound on revenue in deliberative auctions. This bound allows us to apply existing results in the classical environment to a deliberative environment. In addition, we show that in many deliberative environments the only optimal dominant-strategy mechanisms take the form of sequential posted-price auctions.

We consider the problem of designing auctions for settings in Theorem 1 (Dominant strategy impossibility (Larson which bidders have to pay a cost to learn about their preferences, and Sandholm 2004a)). There does not exist any mechanism and hence can face tradeoffs between the cost and accuracy that is strategic deliberation-proof, strategy-dependent, of their preference information. Such bidders are called non-misleading, and preference-formation independent in deliberative agents, and have featured in a wide variety of dominant-strategy equilibrium across all possible quasilinear auction models. For example, costly deliberation can model deliberative-agent settings.