Generative Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Recent research has introduced Multi-Agent Debate (MAD) systems, which leverage multiple LLMs to simulate human debate and thereby improve task performance. However, while some LLMs may possess superior knowledge or reasoning capabilities for specific tasks, they often struggle to clearly communicate this advantage during debates, in part due to a lack of confidence expression. Moreover, inappropriate confidence expression can cause agents in MAD systems to either stubbornly maintain incorrect beliefs or converge prematurely on suboptimal answers, ultimately reducing debate effectiveness and overall system performance. To address these challenges, we propose incorporating confidence expression into MAD systems to allow LLMs to explicitly communicate their confidence levels. To validate this approach, we develop ConfMAD, a MAD framework that integrates confidence expression throughout the debate process. Experimental results demonstrate the effectiveness of our method, and we further analyze how confidence influences debate dynamics, offering insights into the design of confidence-aware MAD systems.

High-quality annotated data is a cornerstone of modern Natural Language Processing (NLP). While recent methods begin to leverage diverse annotation sources-including Large Language Models (LLMs), Small Language Models (SLMs), and human experts-they often focus narrowly on the labeling step itself. A critical gap remains in the holistic process control required to manage these sources dynamically, addressing complex scheduling and quality-cost trade-offs in a unified manner. Inspired by real-world crowdsourcing companies, we introduce CrowdAgent, a multi-agent system that provides end-to-end process control by integrating task assignment, data annotation, and quality/cost management. It implements a novel methodology that rationally assigns tasks, enabling LLMs, SLMs, and human experts to advance synergistically in a collaborative annotation workflow. We demonstrate the effectiveness of CrowdAgent through extensive experiments on six diverse multimodal classification tasks. The source code and video demo are available at https://github.com/QMMMS/CrowdAgent.

Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a systematic literature review to advance the understanding of value alignment in artificial intelligence by characterising the topic in the context of its research literature. We use this to suggest a more precise definition of the term. Methods: We analyse 172 value alignment research articles that have been published in recent years and synthesise their content using thematic analyses. Results: Our analysis leads to six themes: value alignment drivers & approaches; challenges in value alignment; values in value alignment; cognitive processes in humans and AI; human-agent teaming; and designing and developing value-aligned systems. Conclusions: By analysing these themes in the context of the literature we define value alignment as an ongoing process between humans and autonomous agents that aims to express and implement abstract values in diverse contexts, while managing the cognitive limits of both humans and AI agents and also balancing the conflicting ethical and political demands generated by the values in different groups. Our analysis gives rise to a set of research challenges and opportunities in the field of value alignment for future work.

Large Language Model Powered Multi-Agent Systems (MASs) are increasingly employed to automate complex real-world problems, such as programming and scientific discovery. Despite their promising, MASs are not without their flaws. However, failure attribution in MASs - pinpointing the specific agent actions responsible for failures - remains underexplored and labor-intensive, posing significant challenges for debugging and system improvement. To bridge this gap, we propose FAMAS, the first spectrum-based failure attribution approach for MASs, which operates through systematic trajectory replay and abstraction, followed by spectrum analysis.The core idea of FAMAS is to estimate, from variations across repeated MAS executions, the likelihood that each agent action is responsible for the failure. In particular, we propose a novel suspiciousness formula tailored to MASs, which integrates two key factor groups, namely the agent behavior group and the action behavior group, to account for the agent activation patterns and the action activation patterns within the execution trajectories of MASs. Through expensive evaluations against 12 baselines on the Who and When benchmark, FAMAS demonstrates superior performance by outperforming all the methods in comparison.

LLM-based multi-agent simulations are a rapidly growing field of research, but current simulations often lack clear modes for interaction and analysis, limiting the "what if" scenarios researchers are able to investigate. In this demo, we define three core operations for interacting with multi-agent simulations: inject, fork, and compare. Inject allows researchers to introduce external events at any point during simulation execution. Fork creates independent timeline branches from any timestamp, preserving complete state while allowing divergent exploration. Compare facilitates parallel observation of multiple branches, revealing how different interventions lead to distinct emergent behaviors. Together, these operations establish a vocabulary that transforms linear simulation workflows into interactive, explorable spaces. We demonstrate this vocabulary through a commodity market simulation with fourteen AI agents, where researchers can inject contrasting events and observe divergent outcomes across parallel timelines. By defining these fundamental operations, we provide a starting point for systematic causal investigation in LLM-based agent simulations, moving beyond passive observation toward active experimentation.

Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional control over generation. Additionally, in real scenario and online applications, cost considerations, scalability, domain knowledge learning and more precise control are required, presenting more challenge for CTG. This paper introduces a novel and scalable framework, AgentCTG, which aims to enhance precise and complex control over the text generation by simulating the control and regulation mechanisms in multi-agent workflows. We explore various collaboration methods among different agents and introduce an auto-prompt module to further enhance the generation effectiveness. AgentCTG achieves state-of-the-art results on multiple public datasets. To validate its effectiveness in practical applications, we propose a new challenging Character-Driven Rewriting task, which aims to convert the original text into new text that conform to specific character profiles and simultaneously preserve the domain knowledge. When applied to online navigation with role-playing, our approach significantly enhances the driving experience through improved content delivery. By optimizing the generation of contextually relevant text, we enable a more immersive interaction within online communities, fostering greater personalization and user engagement.

Abstract-- Autonomous LLM agents can issue thousands of API calls per hour without human oversight. OAuth 2.0 assumes deterministic clients, but in agentic settings stochastic reasoning, prompt injection, or multi-agent orchestration can silently expand privileges. This paper describes Agentic JWT (A-JWT), a dual-faceted token design that binds each agent action to a cryptographically verifiable user intent and optionally to a workflow step. A-JWT carries an agent's identity as a one-way checksum hash derived from its prompt, tools and configuration and a chained delegation assertion to prove which downstream agent may execute a given task. The design also uses per-agent proof-of-possession keys to prevent replay and in-process impersonation. The paper introduces a new unique authorization grant called'agent_checksum' and adds a lightweight client shim library that self-verifies code at run time, mints intent tokens, tracks workflow steps and derives keys thus enabling secure agent identity and separation even within a single process. We illustrate a comprehensive threat model for agentic applications, implement a Python proof-of-concept, and show functional blocking of scope-violating requests, replay, impersonation, and prompt-injection pathways with sub-millisecond overhead on commodity hardware. The design aligns with ongoing OAuth agent discussions and offers a drop-in path toward zero-trust guarantees for agentic applications. A comprehensive performance and security evaluation with experimental results will appear in our forthcoming journal submission. I. Introduction AI Agents are not a theoretical phenomenon anymore. Large enterprises now use AI agents [1], to possibly execute millions of API calls per hour. Major cloud LLMs now serve hundreds of millions of API requests per day, for example Baidu's ERNIE handles approximately 200 M daily queries, providing the raw horsepower that agent frameworks build on [2], yet those calls still ride on OAuth tokens designed for deterministic clients. A quick peek into the scale of operations and future trends would reveal that the volume of AI Agent activity has grown dramatically, underscoring their operational impact. Baidu's large volume of API calls per day has seen a 4 fold increase in just a few months [2]. A recent cloud survey found OpenAI/Azure AI services are used in 67% of cloud deployments, alongside a rise in self-hosted AI models across 75% of organizations [3].

Trajectory prediction is central to the safe and seamless operation of autonomous vehicles (AVs). In deployment, however, prediction models inevitably face distribution shifts between training data and real-world conditions, where rare or underrepresented traffic scenarios induce out-of-distribution (OOD) cases. While most prior OOD detection research in AVs has concentrated on computer vision tasks such as object detection and segmentation, trajectory-level OOD detection remains largely underexplored. A recent study formulated this problem as a quickest change detection (QCD) task, providing formal guarantees on the trade-off between detection delay and false alarms [1]. Building on this foundation, we propose a new framework that introduces adaptive mechanisms to achieve robust detection in complex driving environments. Empirical analysis across multiple real-world datasets reveals that prediction errors -- even on in-distribution samples -- exhibit mode-dependent distributions that evolve over time with dataset-specific dynamics. By explicitly modeling these error modes, our method achieves substantial improvements in both detection delay and false alarm rates. Comprehensive experiments on established trajectory prediction benchmarks show that our framework significantly outperforms prior UQ- and vision-based OOD approaches in both accuracy and computational efficiency, offering a practical path toward reliable, driving-aware autonomy.

We consider a variant of the target defense problem in a planar conical environment where a single defender is tasked to capture a sequence of incoming attackers. The attackers' objective is to breach the target boundary without being captured by the defender. As soon as the current attacker breaches the target or gets captured by the defender, the next attacker appears at the boundary of the environment and moves radially toward the target with maximum speed. Therefore, the defender's final location at the end of the current game becomes its initial location for the next game. The attackers pick strategies that are advantageous for the current as well as for future engagements between the defender and the remaining attackers. The attackers have their own sensors with limited range, using which they can perfectly detect if the defender is within their sensing range. We derive equilibrium strategies for all the players to optimize the capture percentage using the notions of capture distribution. Finally, the theoretical results are verified through numerical examples using Monte Carlo type random trials of experiments.

We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and allow them to use these tools as they see fit. Across 34 Aider Polyglot Python programming challenges, collaborative tools substantially improve performance on the hardest problems, delivering 15-40% lower cost, 12-27% fewer turns, and 12-38% faster completion than baseline agents. Effects on the full challenge set are mixed, suggesting these tools act as performance enhancers when additional reasoning scaffolding is most needed. Surprisingly, Different models naturally adopted distinct collaborative strategies without explicit instruction. Sonnet 3.7 engaged broadly across tools and benefited from articulation-based cognitive scaffolding. Sonnet 4 showed selective adoption, leaning on journal-based semantic search when problems were genuinely difficult. This mirrors how human developers adjust collaboration based on expertise and task complexity. Behavioral analysis shows agents prefer writing over reading by about 2-9x, indicating that structured articulation drives much of the improvement rather than information access alone. Overall, AI agents can systematically benefit from human-inspired collaboration tools at the edge of their capabilities, pointing to adaptive collaborative interfaces as reasoning enhancers rather than universal efficiency boosts.