Recent advancements in large language models (LLMs) have revolutionized their ability to handle single-turn tasks, yet real-world applications demand sophisticated multi-turn interactions. This survey provides a comprehensive review of recent advancements in evaluating and enhancing multi-turn interactions in LLMs. Focusing on task-specific scenarios, from instruction following in diverse domains such as math and coding to complex conversational engagements in roleplay, healthcare, education, and even adversarial jailbreak settings, we systematically examine the challenges of maintaining context, coherence, fairness, and responsiveness over prolonged dialogues. The paper organizes current benchmarks and datasets into coherent categories that reflect the evolving landscape of multi-turn dialogue evaluation. In addition, we review a range of enhancement methodologies under multi-turn settings, including model-centric strategies (contextual learning, supervised fine-tuning, reinforcement learning, and new architectures), external integration approaches (memory-augmented, retrieval-based methods, and knowledge graph), and agent-based techniques for collaborative interactions. Finally, we discuss open challenges and propose future directions for research to further advance the robustness and effectiveness of multi-turn interactions in LLMs. Related resources and papers are available at https://github.com/yubol-cmu/Awesome-Multi-Turn-LLMs.

--Automated poultry processing lines still rely on humans to lift slippery, easily bruised carcasses onto a shackle conveyor . Deformability, anatomical variance, and strict hygiene rules make conventional suction and scripted motions unreliable. An independently actuated dual-jaw pneumatic gripper clamps both chicken legs, while a conditional diffusion-policy controller, trained from only 50 multi-view teleoperation demonstrations (RGB + proprioception), plans 5-DoF end-effector motion, which includes jaw commands in one shot. On individually presented raw broiler carcasses, our system achieves a 40.6% grasp-and-lift success rate and completes the pick-to-shackle cycle in 38 s, whereas state-of-the-art implicit behaviour cloning (IBC) and LSTM-GMM baselines fail entirely. All CAD, code, and datasets will be open-source. ChicGrasp shows that imitation learning can bridge the gap between rigid hardware and variable bio-products, offering a reproducible benchmark and a public dataset for researchers in agricultural engineering and robot learning. OBOTS and intelligent agents are increasingly deployed in unstructured, dynamic environments where manual programming struggles to capture the intricacies of real-world tasks [1].

In this technical note, we introduce and analyze AWNN: an adaptively weighted nearest neighbor method for performing matrix completion. Nearest neighbor (NN) methods are widely used in missing data problems across multiple disciplines such as in recommender systems and for performing counterfactual inference in panel data settings. Prior works have shown that in addition to being very intuitive and easy to implement, NN methods enjoy nice theoretical guarantees. However, the performance of majority of the NN methods rely on the appropriate choice of the radii and the weights assigned to each member in the nearest neighbor set and despite several works on nearest neighbor methods in the past two decades, there does not exist a systematic approach of choosing the radii and the weights without relying on methods like cross-validation. AWNN addresses this challenge by judiciously balancing the bias variance trade off inherent in weighted nearest-neighbor regression. We provide theoretical guarantees for the proposed method under minimal assumptions and support the theory via synthetic experiments.

Despite decades of research and practice in automated software testing, several fundamental concepts remain ill-defined and under-explored, yet offer enormous potential real-world impact. We show that these concepts raise exciting new challenges in the context of Large Language Models for software test generation. More specifically, we formally define and investigate the properties of hardening and catching tests. A hardening test is one that seeks to protect against future regressions, while a catching test is one that catches such a regression or a fault in new functionality introduced by a code change. Hardening tests can be generated at any time and may become catching tests when a future regression is caught. We also define and motivate the Catching 'Just-in-Time' (JiTTest) Challenge, in which tests are generated 'just-in-time' to catch new faults before they land into production. We show that any solution to Catching JiTTest generation can also be repurposed to catch latent faults in legacy code. We enumerate possible outcomes for hardening and catching tests and JiTTests, and discuss open research problems, deployment options, and initial results from our work on automated LLM-based hardening at Meta. This paper was written to accompany the keynote by the authors at the ACM International Conference on the Foundations of Software Engineering (FSE) 2025. Author order is alphabetical. The corresponding author is Mark Harman.

Generative Adversarial Networks (GANs) are Machine Learning (ML) algorithms that have the ability to address competitive resource allocation problems together with detection and mitigation of anomalous behavior. In this paper, we investigate their use in next-generation (NextG) communications within the context of cognitive networks to address i) spectrum sharing, ii) detecting anomalies, and iii) mitigating security attacks. GANs have the following advantages. First, they can learn and synthesize field data, which can be costly, time consuming, and nonrepeatable. Second, they enable pre-training classifiers by using semi-supervised data. Third, they facilitate increased resolution. Fourth, they enable the recovery of corrupted bits in the spectrum. The paper provides the basics of GANs, a comparative discussion on different kinds of GANs, performance measures for GANs in computer vision and image processing as well as wireless applications, a number of datasets for wireless applications, performance measures for general classifiers, a survey of the literature on GANs for i)-iii) above, and future research directions. As a use case of GAN for NextG communications, we show that a GAN can be effectively applied for anomaly detection in signal classification (e.g., user authentication) outperforming another state-of-the-art ML technique such as an autoencoder.

Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As a result, the integration of RLHF has greatly enhanced the outputs of these large language models (LLMs) and made the interactions and responses appear more "human-like" than those of previous versions using only supervised learning. The increasing convergence of human and machine-written text has potentially severe ethical, sociotechnical, and pedagogical implications relating to transparency, trust, bias, and interpersonal relations. To highlight these implications, this paper presents a rhetorical analysis of some of the central procedures and processes currently being reshaped by RLHF-enhanced generative AI chatbots: upholding language conventions, information seeking practices, and expectations for social relationships. Rhetorical investigations of generative AI and LLMs have, to this point, focused largely on the persuasiveness of the content generated. Using Ian Bogost's concept of procedural rhetoric, this paper shifts the site of rhetorical investigation from content analysis to the underlying mechanisms of persuasion built into RLHF-enhanced LLMs. In doing so, this theoretical investigation opens a new direction for further inquiry in AI ethics that considers how procedures rerouted through AI-driven technologies might reinforce hegemonic language use, perpetuate biases, decontextualize learning, and encroach upon human relationships. It will therefore be of interest to educators, researchers, scholars, and the growing number of users of generative AI chatbots.

Background: The use of social robotics in elderly care is increasingly discussed as one way of meeting emerging care needs due to scarce resources. While many potential benefits are associated with robotic care technologies, there is a variety of ethical challenges. To support steps towards a responsible implementation and use, this review develops an overview on ethical aspects of the use of social robots in elderly care from a decision-makers' perspective. Methods: Electronic databases were queried using a comprehensive search strategy based on the key concepts of "ethical aspects", "social robotics" and "elderly care". Abstract and title screening was conducted by two authors independently. Full-text screening was conducted by one author following a joint consolidation phase. Data was extracted using MAXQDA24 by one author, based on a consolidated coding framework. Analysis was performed through modified qualitative content analysis. Results: A total of 1,518 publications were screened, and 248 publications were included. We have organized our analysis in a scheme of ethical hazards, ethical opportunities and unsettled questions, identifying at least 60 broad ethical aspects affecting three different stakeholder groups. While some ethical issues are well-known and broadly discussed our analysis shows a plethora of potentially relevant aspects, often only marginally recognized, that are worthy of consideration from a practical perspective. Discussion: The findings highlight the need for a contextual and detailed evaluation of implementation scenarios. To make use of the vast knowledge of the ethical discourse, we hypothesize that decision-makers need to understand the specific nature of this discourse to be able to engage in careful ethical deliberation.

Given usefulness of protein language models (LMs) in structure and functional inference, RNA LMs have received increased attentions in the last few years. However, these RNA models are often not compared against the same standard. Here, we divided RNA LMs into three classes (pretrained on multiple RNA types (especially noncoding RNAs), specific-purpose RNAs, and LMs that unify RNA with DNA or proteins or both) and compared 13 RNA LMs along with 3 DNA and 1 protein LMs as controls in zero-shot prediction of RNA secondary structure and functional classification. Results shows that the models doing well on secondary structure prediction often perform worse in function classification or vice versa, suggesting that more balanced unsupervised training is needed.

The integration of Large Language Models (LLMs) and Federated Learning (FL) presents a promising solution for joint training on distributed data while preserving privacy and addressing data silo issues. However, this emerging field, known as Federated Large Language Models (FLLM), faces significant challenges, including communication and computation overheads, heterogeneity, privacy and security concerns. Current research has primarily focused on the feasibility of FLLM, but future trends are expected to emphasize enhancing system robustness and security. This paper provides a comprehensive review of the latest advancements in FLLM, examining challenges from four critical perspectives: feasibility, robustness, security, and future directions. We present an exhaustive survey of existing studies on FLLM feasibility, introduce methods to enhance robustness in the face of resource, data, and task heterogeneity, and analyze novel risks associated with this integration, including privacy threats and security challenges. We also review the latest developments in defense mechanisms and explore promising future research directions, such as few-shot learning, machine unlearning, and IP protection. This survey highlights the pressing need for further research to enhance system robustness and security while addressing the unique challenges posed by the integration of FL and LLM.

This paper introduces Codified Profiles for role-playing, a novel approach that represents character logic as structured, executable functions for behavioral decision-making. Each profile defines a set of functions parse_by_scene(scene) that outputs a list of logic-grounded assertions triggered_statements, using both explicit control structures (e.g., if-then-else) and condition checks like check_condition(scene, question), where each question is a semantically meaningful prompt about the scene (e.g., "Is the character in danger?") discriminated by the role-playing LLM as true, false, or unknown. This explicit representation offers three key advantages over traditional prompt-based profiles, which append character descriptions directly into text prompts: (1) Persistence, by enforcing complete and consistent execution of character logic, rather than relying on the model's implicit reasoning; (2) Updatability, through systematic inspection and revision of behavioral logic, which is difficult to track or debug in prompt-only approaches; (3) Controllable Randomness, by supporting stochastic behavior directly within the logic, enabling fine-grained variability that prompting alone struggles to achieve. To validate these advantages, we introduce a new benchmark constructed from 83 characters and 5,141 scenes curated from Fandom, using NLI-based scoring to compare character responses against ground-truth actions. Our experiments demonstrate the significant benefits of codified profiles in improving persistence, updatability, and behavioral diversity. Notably, by offloading a significant portion of reasoning to preprocessing, codified profiles enable even 1B-parameter models to perform high-quality role-playing, providing a scalable and efficient foundation for local deployment of role-play agents.