Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates this issue by transforming sparse feedback into dense supervision signals. However, previous approaches typically depend on domain-specific value functions for credit assignment, which suffer from poor sample efficiency and limited generalization. In this work, we propose to leverage pre-trained knowledge from large language models (LLMs) to transform sparse rewards into dense training signals (i.e., the advantage function) through retrospective in-context learning (RICL). We further propose an online learning framework, RICOL, which iteratively refines the policy based on the credit assignment results from RICL. We empirically demonstrate that RICL can accurately estimate the advantage function with limited samples and effectively identify critical states for temporal credit assignment. Extended evaluation on the BabyAI benchmark shows that RICOL significantly improves sample efficiency compared to traditional online RL algorithms while achieving performance comparable to imitation learning from expert demonstartions. Our findings highlight the potential of leveraging LLMs for temporal credit assignment, paving the way for more sample-efficient and generalizable RL paradigms.

Humans continuously infer the states, goals, and behaviors of others by perceiving their surroundings in dynamic, real-world social interactions. However, most Theory of Mind (ToM) benchmarks only evaluate static, text-based scenarios, which have a significant gap compared to real interactions. We propose the SoMi-ToM benchmark, designed to evaluate multi-perspective ToM in embodied multi-agent complex social interactions. This benchmark is based on rich multimodal interaction data generated by the interaction environment SoMi, covering diverse crafting goals and social relationships. Our framework supports multi-level evaluation: (1) first-person evaluation provides multimodal (visual, dialogue, action, etc.) input from a first-person perspective during a task for real-time state inference, (2) third-person evaluation provides complete third-person perspective video and text records after a task for goal and behavior inference. This evaluation method allows for a more comprehensive examination of a model's ToM capabilities from both the subjective immediate experience and the objective global observation. We constructed a challenging dataset containing 35 third-person perspective videos, 363 first-person perspective images, and 1225 expert-annotated multiple-choice questions (three options). On this dataset, we systematically evaluated the performance of human subjects and several state-of-the-art large vision-language models (LVLMs). The results show that LVLMs perform significantly worse than humans on SoMi-ToM: the average accuracy gap between humans and models is 40.1% in first-person evaluation and 26.4% in third-person evaluation. This indicates that future LVLMs need to further improve their ToM capabilities in embodied, complex social interactions.

Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi, Maarten Sap, Yonatan Bisk, Graham Neubig, Hao Zhu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

*Humans are social beings*; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and *interact* under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans within this task space and evaluate their performance with a holistic evaluation framework called SOTOPIA-Eval. With SOTOPIA, we find significant differences between these models in terms of their social intelligence, and we identify a subset of SOTOPIA scenarios, SOTOPIA-hard, that is generally challenging for all models. We find that on this subset, GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills. These findings demonstrate SOTOPIA's promise as a general platform for research on evaluating and improving social intelligence in artificial agents.

With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a disconnect with real-world scenarios. In this paper, we build an environment for language-guided agents that is highly realistic and reproducible. Specifically, we focus on agents that perform tasks on the web, and create an environment with fully functional websites from four common domains: e-commerce, social forum discussions, collaborative software development, and content management. Our environment is enriched with tools (e.g., a map) and external knowledge bases (e.g., user manuals) to encourage human-like task-solving. Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. The tasks in our benchmark are diverse, long-horizon, and designed to emulate tasks that humans routinely perform on the internet. We experiment with several baseline agents, integrating recent techniques such as reasoning before acting. The results demonstrate that solving complex tasks is challenging: our best GPT-4-based agent only achieves an end-to-end task success rate of 14.41%, significantly lower than the human performance of 78.24%. These results highlight the need for further development of robust agents, that current state-of-the-art large language models are far from perfect performance in these real-life tasks, and that \ours can be used to measure such progress.\footnote{Code, data, environment reproduction instructions, video demonstrations are available in the supplementary.}

Experience precedes understanding. Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world. On the other hand, machines are either trained to learn passively from static and fixed datasets, or taught to complete specific goal-conditioned tasks. To encourage the development of exploratory interactive agents, we present the EXCALIBUR benchmark. EXCALIBUR allows agents to explore their environment for long durations and then query their understanding of the physical world via inquiries like: “is the small heavy red bowl made from glass?” or “is there a silver spoon heavier than the egg?”. This design encourages agents to perform free-form home exploration without myopia induced by goal conditioning. Once the agents have answered a series of questions, they can renter the scene to refine their knowledge, update their beliefs, and improve their performance on the questions. Our experiments demonstrate the challenges posed by this dataset for the present-day state-of-the-art embodied systems and the headroom afforded to develop new innovative methods. Finally, we present a virtual reality interface that enables humans to seamlessly interact within the simulated world and use it to gather human performance measures. EXCALIBUR affords unique challenges in comparison to presentday benchmarks and represents the next frontier for embodied AI research.

Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange.The recent introduction of benchmarks (Padmakumar et al., 2022) raises the question of how best to train and evaluate models for this multi-turn, multi-agent, long-horizon task.This paper contributes to that conversation, by arguing that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research and may hinder progress.We provide empirical comparisons of metrics, analysis of three models, and make suggestions for how the field might best progress.First, we observe that models trained with IL take spurious actions during evaluation.Second, we find that existing models fail to ground query utterances, which are essential for task completion.Third, we argue evaluation should focus on higher-level semantic goals. 1

Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text.However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of multimodal information leading to improved performance in constituency grammar induction.However, as compared to dependency grammars, constituency grammars do not provide a straightforward way to incorporate visual information without enforcing language-specific heuristics.In this paper, we propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based heuristic to jointly learn constituency-structure and dependency-structure grammars.Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50% as compared to state-of-the-art models trained on pure text.Next, we propose an extension of our model that leverages both word concreteness and visual semantic role labels in constituency and dependency parsing.Our experiments show that the proposed extension outperforms the current state-of-the-art visually grounded models in constituency parsing even with a smaller grammar size. 1

No man is an island. Humans develop the ability to communicate with a large community by coordinating with different interlocutors within short conversations. This ability is largely understudied by the research on building neural language communicative agents. We study the task of few-shot language coordination: agents quickly adapting to their conversational partners’ language abilities. Different from current communicative agents trained with self-play, we in- investigate this more general paradigm by requiring the lead agent to coordinate with a population of agents each of whom has different linguistic abilities. This leads to a general agent able to quickly adapt to communicating with unseen agents in the population. Unlike prior work, success here requires the ability to model the partner’s beliefs, a vital component of human communication. Drawing inspiration from the study of theory-of-mind (ToM; Premack & Woodruff (1978)), we study the effect of the speaker explicitly modeling the listener’s mental state. Learning by communicating with a population, the speakers, as shown in our experiments, acquire the ability to learn to predict the reactions of their partner upon various messages on-the-fly. The speaker’s predictions for the future actions help it generate the best instructions in order to maximize communicative goal with message costs. To examine our hypothesis that the instructions generated with ToM modeling yield better communication per- performance, we employ our agents in both a referential game and a language navigation task. Positive results from our experiments also hint at the importance of explicitly modeling language acquisition as a socio-pragmatic progress.