We study learning in a dynamically evolving environment modeled as a Markov game between a learner and a strategic opponent that can adapt to the learner's strategies. While most existing works in Markov games focus on external regret as the learning objective, external regret becomes inadequate when the adversaries are adaptive. In this work, we focus on \emph{policy regret} -- a counterfactual notion that aims to compete with the return that would have been attained if the learner had followed the best fixed sequence of policy, in hindsight. We show that if the opponent has unbounded memory or if it is non-stationary, then sample-efficient learning is not possible. For memory-bounded and stationary, we show that learning is still statistically hard if the set of feasible strategies for the learner is exponentially large. To guarantee learnability, we introduce a new notion of \emph{consistent} adaptive adversaries, wherein, the adversary responds similarly to similar strategies of the learner. We provide algorithms that achieve $\sqrt{T}$ policy regret against memory-bounded, stationary, and consistent adversaries.

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit unwanted and factually incorrect text. In this work, we propose a novel calibration method that can be used to combat hallucinations. We add a special [IDK] ("I don't know") token to the model's vocabulary and introduce an objective function that shifts probability mass to the [IDK] token for incorrect predictions. This approach allows the model to express uncertainty in its output explicitly. We evaluate our proposed method across multiple model architectures and factual downstream tasks. We find that models trained with our method are able to express uncertainty in places where they would previously make mistakes while suffering only a small loss of encoded knowledge. We further perform extensive ablation studies of multiple variations of our approach and provide a detailed analysis of the precision-recall tradeoff of our method.

While significant progress has been made in task-specific applications, current models struggle with deep reasoning, generality, and adaptation -- key components of System 2 reasoning that are crucial for achieving Artificial General Intelligence (AGI). Despite the promise of approaches such as program synthesis, language models, and transformers, these methods often fail to generalize beyond their training data and to adapt to novel tasks, limiting their ability to perform human-like reasoning. This paper explores the limitations of existing approaches in achieving advanced System 2 reasoning and highlights the importance of generality and adaptation for AGI. Moreover, we propose four key research directions to address these gaps: (1) learning human intentions from action sequences, (2) combining symbolic and neural models, (3) meta-learning for unfamiliar environments, and (4) reinforcement learning to reason multi-step. Through these directions, we aim to advance the ability to generalize and adapt, bringing computational models closer to the reasoning capabilities required for AGI.

This work introduces RARE (Retrieval-Augmented Reasoning Enhancement), a versatile extension to the mutual reasoning framework (rStar), aimed at enhancing reasoning accuracy and factual integrity across large language models (LLMs) for complex, knowledge-intensive tasks such as commonsense and medical reasoning. RARE incorporates two innovative actions within the Monte Carlo Tree Search (MCTS) framework: A6, which generates search queries based on the initial problem statement, performs information retrieval using those queries, and augments reasoning with the retrieved data to formulate the final answer; and A7, which leverages information retrieval specifically for generated sub-questions and re-answers these sub-questions with the relevant contextual information. Additionally, a Retrieval-Augmented Factuality Scorer is proposed to replace the original discriminator, prioritizing reasoning paths that meet high standards of factuality. Experimental results with LLaMA 3.1 show that RARE enables open-source LLMs to achieve competitive performance with top open-source models like GPT-4 and GPT-4o. This research establishes RARE as a scalable solution for improving LLMs in domains where logical coherence and factual integrity are critical.

To develop autonomous agents capable of executing complex, multi-step decision-making tasks as specified by humans in natural language, existing reinforcement learning approaches typically require expensive labeled datasets or access to real-time experimentation. Moreover, conventional methods often face difficulties in generalizing to unseen goals and states, thereby limiting their practical applicability. This paper presents TEDUO, a novel training pipeline for offline language-conditioned policy learning. TEDUO operates on easy-to-obtain, unlabeled datasets and is suited for the so-called in-the-wild evaluation, wherein the agent encounters previously unseen goals and states. To address the challenges posed by such data and evaluation settings, our method leverages the prior knowledge and instruction-following capabilities of large language models (LLMs) to enhance the fidelity of pre-collected offline data and enable flexible generalization to new goals and states. Empirical results demonstrate that the dual role of LLMs in our framework-as data enhancers and generalizers-facilitates both effective and data-efficient learning of generalizable language-conditioned policies.

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning within a much broader spectrum of meta-learned in-context learning. Indeed, we suggest that any distribution of sequences in which context non-trivially decreases loss on subsequent predictions can be interpreted as eliciting a kind of in-context learning. We suggest that this perspective helps to unify the broad set of in-context abilities that language models exhibit $\unicode{x2014}$ such as adapting to tasks from instructions or role play, or extrapolating time series. This perspective also sheds light on potential roots of in-context learning in lower-level processing of linguistic dependencies (e.g. coreference or parallel structures). Finally, taking this perspective highlights the importance of generalization, which we suggest can be studied along several dimensions: not only the ability to learn something novel, but also flexibility in learning from different presentations, and in applying what is learned. We discuss broader connections to past literature in meta-learning and goal-conditioned agents, and other perspectives on learning and adaptation. We close by suggesting that research on in-context learning should consider this broader spectrum of in-context capabilities and types of generalization.

This paper investigates various approaches using Large Language Models (LLMs) to identify gaps and misconceptions in students' self-explanations of specific instructional material, in our case explanations of code examples. This research is a part of our larger effort to automate the assessment of students' freely generated responses, focusing specifically on their self-explanations of code examples during activities related to code comprehension. In this work, we experiment with zero-shot prompting, Supervised Fine-Tuning (SFT), and preference alignment of LLMs to identify gaps in students' self-explanation. With simple prompting, GPT-4 consistently outperformed LLaMA3 and Mistral in identifying gaps and misconceptions, as confirmed by human evaluations. Additionally, our results suggest that fine-tuned large language models are more effective at identifying gaps in students' explanations compared to zero-shot and few-shot prompting techniques. Furthermore, our findings show that the preference optimization approach using Odds Ratio Preference Optimization (ORPO) outperforms SFT in identifying gaps and misconceptions in students' code explanations.

This paper presents a novel approach to compute food composition data for Indian recipes using a knowledge graph for Indian food (FKG.in) and LLMs. The primary focus is to provide a broad overview of an automated food composition analysis workflow and describe its core functionalities: nutrition data aggregation, food composition analysis, and LLM-augmented information resolution. This workflow aims to complement FKG.in and iteratively supplement food composition data from verified knowledge bases. Additionally, this paper highlights the challenges of representing Indian food and accessing food composition data digitally. It also reviews three key sources of food composition data: the Indian Food Composition Tables, the Indian Nutrient Databank, and the Nutritionix API. Furthermore, it briefly outlines how users can interact with the workflow to obtain diet-based health recommendations and detailed food composition information for numerous recipes. We then explore the complex challenges of analyzing Indian recipe information across dimensions such as structure, multilingualism, and uncertainty as well as present our ongoing work on LLM-based solutions to address these issues. The methods proposed in this workshop paper for AI-driven knowledge curation and information resolution are application-agnostic, generalizable, and replicable for any domain.

Emergency communication systems face disruptions due to packet loss, bandwidth constraints, poor signal quality, delays, and jitter in VoIP systems, leading to degraded real-time service quality. Victims in distress often struggle to convey critical information due to panic, speech disorders, and background noise, further complicating dispatchers' ability to assess situations accurately. Staffing shortages in emergency centers exacerbate delays in coordination and assistance. This paper proposes leveraging Large Language Models (LLMs) to address these challenges by reconstructing incomplete speech, filling contextual gaps, and prioritizing calls based on severity. The system integrates real-time transcription with Retrieval-Augmented Generation (RAG) to generate contextual responses, using Twilio and AssemblyAI APIs for seamless implementation. Evaluation shows high precision, favorable BLEU and ROUGE scores, and alignment with real-world needs, demonstrating the model's potential to optimize emergency response workflows and prioritize critical cases effectively.

Graph neural networks (GNNs) are powerful tools for developing scalable, decentralized artificial intelligence in large-scale networked systems, such as wireless networks, power grids, and transportation networks. Currently, GNNs in networked systems mostly follow a paradigm of `centralized training, distributed execution', which limits their adaptability and slows down their development cycles. In this work, we fill this gap for the first time by developing a communication-efficient, fully distributed online training approach for GNNs applied to large networked systems. For a mini-batch with $B$ samples, our approach of training an $L$-layer GNN only adds $L$ rounds of message passing to the $LB$ rounds required by GNN inference, with doubled message sizes. Through numerical experiments in graph-based node regression, power allocation, and link scheduling in wireless networks, we demonstrate the effectiveness of our approach in training GNNs under supervised, unsupervised, and reinforcement learning paradigms.