We present TapeAgents, an agent framework built around a granular, structured log tape of the agent session that also plays the role of the session's resumable state. In TapeAgents we leverage tapes to facilitate all stages of the LLM Agent development lifecycle. The agent reasons by processing the tape and the LLM output to produce new thought and action steps and append them to the tape. The environment then reacts to the agent's actions by likewise appending observation steps to the tape. By virtue of this tape-centred design, TapeAgents can provide AI practitioners with holistic end-to-end support. At the development stage, tapes facilitate session persistence, agent auditing, and step-by-step debugging. Post-deployment, one can reuse tapes for evaluation, fine-tuning, and prompt-tuning; crucially, one can adapt tapes from other agents or use revised historical tapes. In this report, we explain the TapeAgents design in detail. We demonstrate possible applications of TapeAgents with several concrete examples of building monolithic agents and multi-agent teams, of optimizing agent prompts and finetuning the agent's LLM. We present tooling prototypes and report a case study where we use TapeAgents to finetune a Llama-3.1-8B form-filling assistant to perform as well as GPT-4o while being orders of magnitude cheaper. Lastly, our comparative analysis shows that TapeAgents's advantages over prior frameworks stem from our novel design of the LLM agent as a resumable, modular state machine with a structured configuration, that generates granular, structured logs and that can transform these logs into training text -- a unique combination of features absent in previous work.

Epistemic planning is the sub-field of AI planning that focuses on changing knowledge and belief. It is important in both multi-agent domains where agents need to have knowledge/belief regarding the environment, but also the beliefs of other agents, including nested beliefs. When modeling knowledge in multi-agent settings, many models face an exponential growth challenge in terms of nested depth. A contemporary method, known as Planning with Perspectives (PWP), addresses these challenges through the use of perspectives and set operations for knowledge. The JP model defines that an agent's belief is justified if and only if the agent has seen evidence that this belief was true in the past and has not seen evidence to suggest that this has changed. The current paper extends the JP model to handle \emph{group belief}, including distributed belief and common belief. We call this the Group Justified Perspective (GJP) model. Using experimental problems crafted by adapting well-known benchmarks to a group setting, we show the efficiency and expressiveness of our GJP model at handling planning problems that cannot be handled by other epistemic planning tools.

The increasing rates of global urbanization and vehicle usage are leading to a shift of mobility to the third dimension-through Advanced Air Mobility (AAM)-offering a promising solution for faster, safer, cleaner, and more efficient transportation. As air transportation continues to evolve with more automated and autonomous systems, advancements in AAM require a deep understanding of human-computer interaction and human-AI collaboration to ensure safe and effective operations in complex urban and regional environments. There has been a significant increase in publications regarding these emerging applications; thus, there is a need to review developments in this area. This paper comprehensively reviews the current state of research on human-computer interaction and human-AI collaboration in AAM. Specifically, we focus on AAM applications related to the design of human-machine interfaces for various uses, including pilot training, air traffic management, and the integration of AI-assisted decision-making systems with immersive technologies such as extended, virtual, mixed, and augmented reality devices. Additionally, we provide a comprehensive analysis of the challenges AAM encounters in integrating human-computer frameworks, including unique challenges associated with these interactions, such as trust in AI systems and safety concerns. Finally, we highlight emerging opportunities and propose future research directions to bridge the gap between human factors and technological advancements in AAM.

This paper presents the application of Tokenlab, an agent-based modeling framework designed to analyze price dynamics and speculative behavior within token-based economies. By decomposing complex token systems into discrete agent interactions governed by fundamental behavioral rules, Tokenlab simplifies the simulation of otherwise intricate market scenarios. Its core innovation lies in its ability to model a range of speculative strategies and assess their collective influence on token price evolution. Through a novel controller mechanism, Tokenlab facilitates the simulation of multiple speculator archetypes and their interactions, thereby providing valuable insights into market sentiment and price formation. This method enables a systematic exploration of how varying degrees of speculative activity and evolving strategies across different market stages shape token price trajectories. Our findings enhance the understanding of speculation in token markets and present a quantitative framework for measuring and interpreting market heat indicators.

Norms and the normative processes that enforce them such as social maintenance are considered fundamental building blocks of human societies, shaping many aspects of our cognition. However, emerging work argues that the building blocks of normativity emerged much earlier in evolution than previously considered. In light of this, we argue that normative processes must be taken into account to consider the evolution of even ancient processes such as affect. We show through an agent-based model (with an evolvable model of affect) that different affective dispositions emerge when taking into account social maintenance. Further, we demonstrate that social maintenance results in the emergence of a minimal population regulation mechanism in a dynamic environment, without the need to predict the state of the environment or reason about the mental state of others. We use a cultural interpretation of our model to derive a new definition of norm emergence which distinguishes between indirect and direct social maintenance. Indirect social maintenance tends to one equilibrium (similar to environmental scaffolding) and the richer direct social maintenance results in many possible equilibria in behaviour, capturing an important aspect of normative behaviour in that it bears a certain degree of arbitrariness. We also distinguish between single-variable and mechanistic normative regularities. A mechanistic regularity, rather than a particular behaviour specified by one value e.g. walking speed, is a collection of values that specify a culturally patterned version of a psychological mechanism e.g. a disposition. This is how culture reprograms entire cognitive and physiological systems.

Epistemic Planning (EP) is an important research area dedicated to reasoning about the knowledge and beliefs of agents in multi-agent cooperative or adversarial settings. The Justified Perspective (JP) model is the state-of-the-art approach to solving EP problems with efficiency and expressiveness. However, all existing EP methods inherit the static environment assumption from classical planning. This limitation hinders the application of EP in fields such as robotics with multi-agent settings, where the environment contains changing variables. In this paper, we propose an extension of the JP model, namely, the Predictive Justified Perspective (PJP) model, to remove this assumption. Instead of assuming that beliefs remain unchanged since the last observation, the PJP model uses all past observations to form predictions about the changing variables. The definition of the prediction function with examples is provided, and it is demonstrated that it can work with arbitrary nesting. We then implemented the PJP model in several well-known domains and compared it with the JP model in the experiments. The results indicated that the PJP model performs exceptionally well across various domains, demonstrating its potential in improving EP applications in robotics.

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications, challenging agents with managing risks encompassing misuse and negative side effects. These tasks include tests to evaluate the safety of agents in daily scenarios as well as their robustness against indirect prompt injection attacks. Our experiments demonstrate that baseline agents, based on state-of-the-art LLMs, often fail to effectively prevent harm while performing the tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments. We open-source our benchmark at: https://mobilesafetybench.github.io/.

Learning from human feedback is a popular approach to train robots to adapt to user preferences and improve safety. Existing approaches typically consider a single querying (interaction) format when seeking human feedback and do not leverage multiple modes of user interaction with a robot. We examine how to learn a penalty function associated with unsafe behaviors, such as side effects, using multiple forms of human feedback, by optimizing the query state and feedback format. Our framework for adaptive feedback selection enables querying for feedback in critical states in the most informative format, while accounting for the cost and probability of receiving feedback in a certain format. We employ an iterative, two-phase approach which first selects critical states for querying, and then uses information gain to select a feedback format for querying across the sampled critical states. Our evaluation in simulation demonstrates the sample efficiency of our approach.

The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs). However, producing RTL code that is both syntactically and functionally correct remains a significant challenge. Existing single-LLM-agent approaches face substantial limitations because they must navigate between various programming languages and handle intricate generation, verification, and modification tasks. To address these challenges, this paper introduces MAGE, the first open-source multi-agent AI system designed for robust and accurate Verilog RTL code generation. We propose a novel high-temperature RTL candidate sampling and debugging system that effectively explores the space of code candidates and significantly improves the quality of the candidates. Furthermore, we design a novel Verilog-state checkpoint checking mechanism that enables early detection of functional errors and delivers precise feedback for targeted fixes, significantly enhancing the functional correctness of the generated RTL code. MAGE achieves a 95.7% rate of syntactic and functional correctness code generation on VerilogEval-Human 2 benchmark, surpassing the state-of-the-art Claude-3.5-sonnet by 23.3 %, demonstrating a robust and reliable approach for AI-driven RTL design workflows.

In implicit emotion analysis (IEA), the subtlety of emotional expressions makes it particularly sensitive to user-specific characteristics. Existing studies often inject personalization into the analysis by focusing on the authorial dimension of the emotional text. However, these methods overlook the potential influence of the intended reader on the reaction of implicit emotions. In this paper, we refine the IEA task to Personalized Implicit Emotion Analysis (PIEA) and introduce the RAPPIE model, a novel framework designed to address the issue of missing user information within this task. In particular, 1) we create reader agents based on the Large Language Model to simulate reader reactions, to address challenges of the spiral of silence and data incompleteness encountered when acquiring reader feedback information. 2) We establish a reader propagation role system and develop a role-aware emotion propagation multi-view graph learning model, which effectively deals with the sparsity of reader information by utilizing the distribution of propagation roles. 3) We annotate two Chinese PIEA datasets with detailed user metadata, thereby addressing the limitation of prior datasets that primarily focus on textual content annotation. Extensive experiments on these datasets indicate that the RAPPIE model outperforms current state-of-the-art baselines, highlighting the significance and efficacy of incorporating reader feedback into the PIEA process.