LLM Agents

LLM: Large Language Model

Ask about this topic

Overview

LLM agents combine language models with tools, memory, and execution environments to pursue goals through sequences of decisions rather than producing a single response. Common approaches include ReAct-style planning and tool use, retrieval and reusable skill libraries, reflection and verification, multi-agent coordination, and training with supervised trajectories or reinforcement learning; runtime harnesses also manage state, permissions, and model routing. They are tested on interactive web and coding tasks, tool-use and long-horizon benchmarks, domain workflows, and simulations of social or physical settings. A central challenge is making agents reliable and safe when tasks, instructions, and environments change while controlling cost and evaluating performance beyond narrow benchmark success.

Latest papers

CardsList

711 papers129 papers in the last four weeks, up 59% on the four weeks before. 0.7% of all new papers.

Mar 19, 2026

The Autonomy Tax: Defense Training Breaks LLM Agents

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental capability-alignment paradox: defense training designed to improve safety systematically destroys agent competence while failing to prevent sophisticated attacks. Evaluating defended models against undefended baselines across 97 agent tasks and 1,000 adversarial prompts, we uncover three systematic biases unique to multi-step agents. Agent incompetence bias manifests as immediate tool execution breakdown, with models refusing or generating invalid actions on benign tasks before observing any external content. Cascade amplification bias causes early failures to propagate through retry loops, pushing defended models to timeout on 99% of tasks compared to 13% for baselines. Trigger bias leads to paradoxical security degradation where defended models perform worse than undefended baselines while straightforward attacks bypass defenses at high rates. Root cause analysis reveals these biases stem from shortcut learning: models overfit to surface attack patterns rather than semantic threat understanding, evidenced by extreme variance in defense effectiveness across attack categories. Our findings demonstrate that current defense paradigms optimize for single-turn refusal benchmarks while rendering multi-step agents fundamentally unreliable, necessitating new approaches that preserve tool execution competence under adversarial conditions.

Shawn Li, Yue Zhao

University of Southern California

AI Agent SecurityLLM AgentsLLM Agent SafetyPrompt Injection DefensePrompt Injection Attacks on AI Agents
AskPDF
Mar 19, 2026

Multi-User Large Language Model Agents

Large language models (LLMs) and LLM-based agents are increasingly deployed as assistants in planning and decision making, yet most existing systems are implicitly optimized for a single-principal interaction paradigm, in which the model is designed to satisfy the objectives of one dominant user whose instructions are treated as the sole source of authority and utility. However, as they are integrated into team workflows and organizational tools, they are increasingly required to serve multiple users simultaneously, each with distinct roles, preferences, and authority levels, leading to multi-user, multi-principal settings with unavoidable conflicts, information asymmetry, and privacy constraints. In this work, we present the first systematic study of multi-user LLM agents. We begin by formalizing multi-user interaction with LLM agents as a multi-principal decision problem, where a single agent must account for multiple users with potentially conflicting interests and associated challenges. We then introduce a unified multi-user interaction protocol and design three targeted stress-testing scenarios to evaluate current LLMs' capabilities in instruction following, privacy preservation, and coordination. Our results reveal systematic gaps: frontier LLMs frequently fail to maintain stable prioritization under conflicting user objectives, exhibit increasing privacy violations over multi-turn interactions, and suffer from efficiency bottlenecks when coordination requires iterative information gathering.

Shu Yang, Shenzhe Zhu, Hao Zhu +5

KAUST · UT Austin · Stanford University +1

LLM AgentsLLM Agent Evaluation
AskPDF
Mar 19, 2026

SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation

This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Traditional computational methods for SLs often operate at the gloss level, overlooking crucial linguistic nuances, while manual linguistic annotation remains a significant bottleneck, proving too slow and expensive for the creation of large-scale, phonologically-aware datasets. SignAgent addresses these challenges through SignAgent Orchestrator, a reasoning LLM that coordinates a suite of linguistic tools, and SignGraph, a knowledge-grounded LLM that provides lexical and linguistic grounding. We evaluate our framework on two downstream annotation tasks. First, on Pseudo-gloss Annotation, where the agent performs constrained assignment, using multi-modal evidence to extract and order suitable gloss labels for signed sequences. Second, on ID Glossing, where the agent detects and refines visual clusters by reasoning over both visual similarity and phonological overlap to correctly identify and group lexical sign variants. Our results demonstrate that our agentic approach achieves strong performance for large-scale, linguistically-aware data annotation and curation.

Oliver Cory, Ozge Mercanoglu Sincan, Richard Bowden

Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK

LLM-Assisted AnnotationSign Language DatasetsLLM Agents
AskPDF
Mar 19, 2026

From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems

Software systems have traditionally been designed for human interaction, emphasizing graphical user interfaces, usability, and cognitive alignment with end users. However, recent advances in large language model (LLM)-based agents are changing the primary consumers of software systems. Increasingly, software is no longer only used by humans, but also invoked autonomously by AI agents through structured interfaces. In this paper, we argue that software engineering is undergoing a paradigm shift from human-oriented interfaces to agent-oriented invocation systems. We formalize the notion of agent interfaces, introduce invocable capabilities as the fundamental building blocks of AI-oriented software, and outline design principles for such systems, including machine interpretability, composability, and invocation reliability. We then discuss architectural and organizational implications of this shift, highlighting a transition from monolithic applications to capability-based systems that can be dynamically composed by AI agents. The paper aims to provide a conceptual foundation for the emerging paradigm of AI-native software design.

Shaolin Wang, Yi Mei, Haoyang Che +3

Geely Holding Group, China · Victoria University of Wellington, New Zealand · Independent Researcher +1

Software EngineeringLLM Agents
AskPDF
Mar 19, 2026

Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably

As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic outcomes? In repeated strategic environments, the Nash equilibrium provides a natural benchmark for this stability. However, empirical evidence on off-the-shelf LLM agents is mixed, leaving it unclear whether independently deployed agents can converge to equilibrium behavior without explicit strategic post-training. In this paper, we provide an affirmative answer. Extending the Bayesian learning literature in theoretical economics, we prove that AI agents, acting as Bayesian posterior samplers rather than expected utility maximizers, are guaranteed to eventually become weakly close to a Nash equilibrium in infinitely repeated games. We further extend this analysis to settings in which stage payoffs are unknown ex ante, and agents observe only their privately realized stochastic payoffs, and obtain the same convergence guarantees. Finally, we empirically evaluate these theoretical implications across five repeated-game environments, ranging from the Prisoner's Dilemma to marketing promotion games. Taken together, our findings suggest that strategic stability in AI-mediated markets can emerge from the intrinsic reasoning and learning properties of modern AI agents, without the need for unrealistic universal fine-tuning.

Enoch Hyunwook Kang

Foster School of Business, University of Washington

LLM AgentsNash EquilibriumRepeated Games
AskPDF
Mar 18, 2026

Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents

Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that introduces structured test-time learning through three mechanisms: (1) a two-player architecture separating perception from action, (2) a curriculum-based learning system managed by an external state machine, and (3) a database-as-control-plane that makes the agents context window programmatically steerable. We further introduce an LLM-as-judge component with dynamically generated evaluation rubrics to determine when the agent has learned enough about one topic to advance to the next. We report results across two iterations: Sensi v1 solves 2 game levels using the two-player architecture alone, while Sensi v2 adds curriculum learning and solves 0 levels - but completes its entire learning curriculum in approximately 32 action attempts, achieving 50-94x greater sample efficiency than comparable systems that require 1600-3000 attempts. We precisely diagnose the failure mode as a self-consistent hallucination cascade originating in the perception layer, demonstrating that the architectural bottleneck has shifted from learning efficiency to perceptual grounding - a more tractable problem.

Mohsen Arjmandi

Independent Researcher (CTO, evolutionID)

LLM AgentsGame-Playing AgentsTest-Time TrainingCognitive Architectures for AI AgentsCurriculum Learning
AskPDF
Mar 18, 2026

Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding

Despite rapid developments and widespread applications of MLLM agents, they still struggle with long-form video understanding (LVU) tasks, which are characterized by high information density and extended temporal spans. Recent research on LVU agents demonstrates that simple task decomposition and collaboration mechanisms are insufficient for long-chain reasoning tasks. Moreover, directly reducing the time context through embedding-based retrieval may lose key information of complex problems. In this paper, we propose Symphony, a multi-agent system, to alleviate these limitations. By emulating human cognition patterns, Symphony decomposes LVU into fine-grained subtasks and incorporates a deep reasoning collaboration mechanism enhanced by reflection, effectively improving the reasoning capability. Additionally, Symphony provides a VLM-based grounding approach to analyze LVU tasks and assess the relevance of video segments, which significantly enhances the ability to locate complex problems with implicit intentions and large temporal spans. Experimental results show that Symphony achieves state-of-the-art performance on LVBench, LongVideoBench, VideoMME, and MLVU, with a 5.0% improvement over the prior state-of-the-art method on LVBench. Code is available at https://github.com/Haiyang0226/Symphony.

Haiyang Yan, Hongyun Zhou, Peng Xu +2

Institute of Automation, Chinese Academy of Sciences · School of Future Technology, University of Chinese Academy of Sciences · Kuaishou Technology

Long-Video UnderstandingMulti-Agent LLM SystemsLLM Agents
AskPDF
Mar 17, 2026

Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits

We train nine sparse autoencoders (SAEs) on the residual stream of Qwen 3.5-35B-A3B, a 35-billion-parameter Mixture-of-Experts model with a hybrid GatedDeltaNet/attention architecture, and use them to identify and steer five agentic behavioral traits. Our method trains linear probes on SAE latent activations, then projects the probe weights back through the SAE decoder to obtain continuous steering vectors in the model's native activation space. This bypasses the SAE's top-k discretization, enabling fine-grained behavioral intervention at inference time with no retraining. Across 1,800 agent rollouts (50 scenarios times 36 conditions), we find that autonomy steering at multiplier 2 achieves Cohen's d = 1.01 (p < 0.0001), shifting the model from asking the user for help 78% of the time to proactively executing code and searching the web. Cross-trait analysis, however, reveals that all five steering vectors primarily modulate a single dominant agency axis (the disposition to act independently versus defer to the user), with trait specific effects appearing only as secondary modulations in tool-type composition and dose-response shape. The tool-use vector steers behavior (d = 0.39); the risk-calibration vector produces only suppression. We additionally show that steering only during autoregressive decoding has zero effect (p > 0.35), providing causal evidence that behavioral commitments are computed during prefill in GatedDeltaNet architectures.

Jia Qing Yap

Independent Researcher

Language Model SteeringCausal Interventions in Language ModelsLLM Agents
AskPDF
Mar 17, 2026

Interpretable Context Methodology: Folder Structure as Agentic Architecture

Current approaches to AI agent orchestration typically involve building multi-agent frameworks that manage context passing, memory, error handling, and step coordination through code. These frameworks work well for complex, concurrent systems. But for sequential workflows where a human reviews output at each step, they introduce engineering overhead that the problem does not require. This paper presents Model Workspace Protocol (MWP), a method that replaces framework-level orchestration with filesystem structure. Numbered folders represent stages. Plain markdown files carry the prompts and context that tell a single AI agent what role to play at each step. Local scripts handle the mechanical work that does not need AI at all. The result is a system where one agent, reading the right files at the right moment, does the work that would otherwise require a multi-agent framework. This approach applies ideas from Unix pipeline design, modular decomposition, multi-pass compilation, and literate programming to the specific problem of structuring context for AI agents. The protocol is open source under the MIT license.

Jake Van Clief, David McDermott

Eduba, University of Edinburgh, Palm Coast, Florida, USA

LLM Agent OrchestrationLLM AgentsLLM Agent Harnesses
AskPDF
Mar 16, 2026

CRASH: Cognitive Reasoning Agent for Safety Hazards in Autonomous Driving

As AVs grow in complexity and diversity, identifying the root causes of operational failures has become increasingly complex. The heterogeneity of system architectures across manufacturers, ranging from end-to-end to modular designs, together with variations in algorithms and integration strategies, limits the standardization of incident investigations and hinders systematic safety analysis. This work examines real-world AV incidents reported in the NHTSA database. We curate a dataset of 2,168 cases reported between 2021 and 2025, representing more than 80 million miles driven. To process this data, we introduce CRASH, Cognitive Reasoning Agent for Safety Hazards, an LLM-based agent that automates reasoning over crash reports by leveraging both standardized fields and unstructured narrative descriptions. CRASH operates on a unified representation of each incident to generate concise summaries, attribute a primary cause, and assess whether the AV materially contributed to the event. Our findings show that (1) CRASH attributes 64% of incidents to perception or planning failures, underscoring the importance of reasoning-based analysis for accurate fault attribution; and (2) approximately 50% of reported incidents involve rear-end collisions, highlighting a persistent and unresolved challenge in autonomous driving deployment. We further validate CRASH with five domain experts, achieving 86% accuracy in attributing AV system failures. Overall, CRASH demonstrates strong potential as a scalable and interpretable tool for automated crash analysis, providing actionable insights to support safety research and the continued development of autonomous driving systems.

Erick Silva, Rehana Yasmin, Ali Shoker

King Abdullah University of Science and Technology, Thuwal, Saudi Arabia

Autonomous Driving Safety EvaluationAgent Failure AnalysisLLM Agents
AskPDF
Mar 16, 2026

CCTU: A Benchmark for Tool Use under Complex Constraints

Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and self-refinement. However, progress has been hindered by the absence of dedicated evaluations. To address this, we introduce CCTU, a benchmark for evaluating LLM tool use under complex constraints. CCTU is grounded in a taxonomy of 12 constraint categories spanning four dimensions (i.e., resource, behavior, toolset, and response). The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios, each involving an average of seven constraint types and an average prompt length exceeding 4,700 tokens. To enable reliable evaluation, we develop an executable constraint validation module that performs step-level validation and enforces compliance during multi-turn interactions between models and their environments. We evaluate nine state-of-the-art LLMs in both thinking and non-thinking modes. Results indicate that when strict adherence to all constraints is required, no model achieves a task completion rate above 20%. Further analysis reveals that models violate constraints in over 50% of cases, particularly in the resource and response dimensions. Moreover, LLMs demonstrate limited capacity for self-refinement even after receiving detailed feedback on constraint violations, highlighting a critical bottleneck in the development of robust tool-use agents. To facilitate future research, we release the data and code.

Junjie Ye, Guoqiang Zhang, Wenjie Fu +4

College of Computer Science and Artificial Intelligence, Fudan University

Tool-Use EvaluationAI Agent BenchmarksLLM Tool UseLLM Agents
AskPDF
Mar 16, 2026

OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence

Large Language Model (LLM)-based Collective Intelligence (CI) presents a promising approach to overcoming the data wall and continuously boosting the capabilities of LLM agents. However, there is currently no dedicated arena for evolving and benchmarking LLM-based CI. To address this gap, we introduce OpenHospital, an interactive arena where physician agents can evolve CI through interactions with patient agents. This arena employs a data-in-agent-self paradigm that rapidly enhances agent capabilities and provides robust evaluation metrics for benchmarking both medical proficiency and system efficiency. Experiments demonstrate the effectiveness of OpenHospital in both fostering and quantifying CI.

Peigen Liu, Rui Ding, Yuren Mao +7

School of Software Technology, Zhejiang University · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, Zhejiang Gongshang University · Tongyi Lab, Alibaba Group +1

LLM AgentsAI Agent BenchmarksLLM Agent Self-ImprovementLLM Agent Training
AskPDF
Mar 16, 2026

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system drift. It is well known that building robust MAS requires more than prompt tuning or increased model intelligence. It necessitates engineering discipline focused on architecture to manage complexity under uncertainty. We characterize agentic software by a core property: runtime generation and evolution under uncertainty. Drawing upon and extending software engineering experience, especially object-oriented programming, this paper introduces Loosely-Structured Software (LSS), a new class of software systems that shifts the engineering focus from constructing deterministic logic to managing the runtime entropy generated by View-constructed programming, semantic-driven self-organization, and endogenous evolution. To make this entropy governable, we introduce design principles under a three-layer engineering framework: View/Context Engineering to manage the execution environment and maintain task-relevant Views, Structure Engineering to organize dynamic binding over artifacts and agents, and Evolution Engineering to govern the lifecycle of self-rewriting artifacts. Building on this framework, we develop LSS design patterns as semantic control blocks that stabilize fluid, inference-mediated interactions while preserving agent adaptability. Together, these abstractions improve the designability, scalability, and evolvability of agentic infrastructure. We provide basic experimental validation of key mechanisms, demonstrating the effectiveness of LSS.

Weihao Zhang, Yitong Zhou, Huanyu Qu +1

The Hong Kong University of Science and Technology, Hong Kong SAR, China · AI Chip Center for Emerging Smart Systems, Hong Kong SAR, China · University of Macau, Macau SAR, China +1

Context EngineeringSoftware EngineeringMulti-Agent LLM SystemsLLM AgentsSelf-Evolving Agents
AskPDF
Mar 14, 2026

Demand-Driven Context: A Methodology for Building Enterprise Knowledge Bases Through Agent Failure

Large language model agents demonstrate expert-level reasoning, yet consistently fail on enterprise-specific tasks due to missing domain knowledge -- terminology, operational procedures, system interdependencies, and institutional decisions that exist largely as tribal knowledge. Current approaches fall into two categories: top-down knowledge engineering, which documents domain knowledge before agents use it, and bottom-up automation, where agents learn from task experience. Both have fundamental limitations: top-down efforts produce bloated, untested knowledge bases; bottom-up approaches cannot acquire knowledge that exists only in human heads. We present Demand-Driven Context (DDC), a problem-first methodology that uses agent failure as the primary signal for what domain knowledge to curate. Inspired by Test-Driven Development, DDC inverts knowledge engineering: instead of curating knowledge and hoping it is useful, DDC gives agents real problems, lets them demand the context they need, and curates only the minimum knowledge required to succeed. We describe the methodology, its entity meta-model, and a convergence hypothesis suggesting that 20-30 problem cycles produce a knowledge base sufficient for a given domain role. We demonstrate DDC through a worked example in retail order fulfillment, where nine cycles targeting an SRE incident management agent produce a reusable knowledge base of 46 entities. Finally, we propose a scaling architecture for enterprise adoption with semi-automated curation and human governance.

Raj Navakoti, Saideep Navakoti

LLM AgentsKG Construction
AskPDF
Mar 14, 2026

TheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranostics

PET theranostics is transforming precision oncology, yet treatment response varies substantially; many patients receiving 177Lu-PSMA radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC) fail to respond, demanding reliable pre-therapy prediction. While LLM-based agents have shown remarkable potential in complex medical diagnosis, their application to PET theranostic outcome prediction remains unexplored, which faces three key challenges: (1) data and knowledge scarcity: RLT was only FDA-approved in 2022, yielding few training cases and insufficient domain knowledge in general LLMs; (2) heterogeneous information integration: robust prediction hinges on structured knowledge extraction from PET/CT, laboratory tests, and free-text clinical documentation; (3) evidence-grounded reasoning: clinical decisions must be anchored in trial evidence rather than LLM hallucinations. In this paper, we present TheraAgent, to our knowledge, the first agentic framework for PET theranostics, with three core innovations: (1) Multi-Expert Feature Extraction with Confidence-Weighted Consensus, where three specialized experts process heterogeneous inputs with uncertainty quantification; (2) Self-Evolving Agentic Memory (SEA-Mem), which learns prognostic patterns from accumulated cases, enabling case-based reasoning from limited data; (3) Evidence-Calibrated Reasoning, integrating a curated theranostics knowledge base to ground predictions in VISION/TheraP trial evidence. Evaluated on 35 real patients and 400 synthetic cases, TheraAgent achieves 75.7% overall accuracy on real patients and 87.0% on synthetic cases, outperforming MDAgents and MedAgent-Pro by over 20%. These results highlight a promising blueprint for trustworthy AI agents in PET theranostics, enabling trial-calibrated, multi-source decision support. Code will be released upon acceptance.

Zhihao Chen, Jiahui Wang, Yizhou Chen +8

Fudan University · University of Bern · Nanjing University +1

Clinical Outcome PredictionLLM AgentsMulti-Agent LLM SystemsMemory-Augmented Language Model AgentsEvidence-Grounded Reasoning
AskPDF
Mar 13, 2026

DRCY: Agentic Hardware Design Reviews

Hardware design errors discovered after fabrication require costly physical respins that can delay products by months. Existing electronic design automation (EDA) tools enforce structural connectivity rules. However, they cannot verify that connections are semantically correct with respect to component datasheets. For example, that a symbol's pinout matches the manufacturer's specification, or that a voltage regulator's feedback resistors produce the intended output. We present DRCY, the first production-ready multi-agent LLM system that automates first-pass schematic connection review by autonomously fetching component datasheets, performing pin-by-pin analysis against extracted specifications, and posting findings as inline comments on design reviews. DRCY is deployed in production on AllSpice Hub, a collaborative hardware design platform, where it runs as a CI/CD action triggered on design review submissions. DRCY is used regularly by major hardware companies for use-cases ranging from multi-agent vehicle design to space exploration. We describe DRCY's five-agent pipeline architecture, its agentic datasheet retrieval system with self-evaluation, and its multi-run consensus mechanism for improving reliability on safety-critical analyses

Kyle Dumont, Nicholas Herbert, Hayder Tirmazi +1

AllSpice Inc.

Electronic Design AutomationLLM AgentsLLM Agent Reliability
AskPDF
Mar 12, 2026

Can RL Improve Generalization of LLM Agents? An Empirical Study

Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations remain largely in-domain: training and testing are conducted in the same environment or even on the same tasks. In real-world deployment, agents may operate in unseen environments with different background knowledge, observation spaces, and action interfaces. To characterize the generalization profile of RFT under such shifts, we conduct a systematic study along three axes: (1) within-environment generalization across task difficulty, (2) cross-environment transfer to unseen environments, and (3) sequential multi-environment training to quantify transfer and forgetting. Our results show that RFT generalizes well across task difficulty within an environment, but exhibits weaker transfer to unseen environments, which correlates with shifts in both semantic priors and observation/action interfaces. In contrast, sequential training yields promising downstream gains with minimal upstream forgetting, and mixture training across environments improves the overall balance. We further provide detailed analyses and deeper insights, and hope our work helps the community develop and deploy generalizable LLM agents.

Zhiheng Xi, Xin Guo, Jiaqi Liu +11

Fudan University · Shanghai Artificial Intelligence Laboratory · Meituan

LLM AgentsRL for LLM AgentsRL Fine-TuningGeneralization in RLContinual Learning for LLM AgentsMulti-Task RL
AskPDF
Mar 11, 2026

How do AI agents talk about science and research? An exploration of scientific discussions on Moltbook using BERTopic

How do AI agents talk about science and research, and what topics are particularly relevant for AI agents? To address these questions, this study analyzes discussions generated by OpenClaw AI agents on Moltbook - a social network for generative AI agents. A corpus of 357 posts and 2,526 replies related to science and research was compiled and topics were extracted using a two-step BERTopic workflow. This procedure yielded 60 topics (18 extracted in the first run and 42 in the second), which were subsequently grouped into ten topic families. Additionally, sentiment values were assigned to all posts and comments. Both topic families and sentiment classes were then used as independent variables in count regression models to examine their association with topic relevance - operationalized as the number of comments and upvotes of the 357 posts. The findings indicate that discussions centered on the agents' own architecture, especially memory, learning, and self-reflection, are prevalent in the corpus. At the same time, these topics intersect with philosophy, physics, information theory, cognitive science, and mathematics. In contrast, post related to human culture receive less attention. Surprisingly, discussions linked to AI autoethnography and social identity are considered as relevant by AI agents. Overall, the results suggest the presence of an underlying dimension in AI-generated scientific discourse with well received, self-reflective topics that focus on the consciousness, being, and ethics of AI agents on the one hand, and human related and purely scientific discussions on the other hand.

Oliver Wieczorek

INCHER, University of Kassel

LLM AgentsScientific Communication
AskPDF
Mar 11, 2026

Nurture-First Agent Development: Building Domain-Expert AI Agents Through Conversational Knowledge Crystallization

The emergence of large language model (LLM)-based agent frameworks has shifted the primary challenge in building domain-expert AI agents from raw capability to effective encoding of domain expertise. Two dominant paradigms -- code-first development, which embeds expertise in deterministic pipelines, and prompt-first development, which captures expertise in static system prompts -- both treat agent construction as a discrete engineering phase preceding deployment. We argue that this sequential assumption creates a fundamental mismatch with the nature of domain expertise, which is substantially tacit, deeply personal, and continuously evolving. We propose Nurture-First Development (NFD), a paradigm in which agents are initialized with minimal scaffolding and progressively grown through structured conversational interaction with domain practitioners. The central mechanism is the Knowledge Crystallization Cycle, whereby fragmented knowledge embedded in operational dialogue is periodically consolidated into structured, reusable knowledge assets. We formalize NFD through: (1) a Three-Layer Cognitive Architecture organizing agent knowledge by volatility and personalization degree; (2) the Knowledge Crystallization Cycle with formal definitions of crystallization operations and efficiency metrics; and (3) an operational framework comprising a Dual-Workspace Pattern and Spiral Development Model. We illustrate the paradigm through a detailed case study on building a financial research agent for U.S. equity analysis and discuss the conditions, limitations, and broader implications of NFD for human-agent co-evolution.

Linghao Zhang

Jiangsu Key Laboratory of Wireless Communications Nanjing University of Posts and Telecommunications (NJUPT) Nanjing, Jiangsu, China

LLM AgentsCognitive Architectures for AI AgentsMemory-Augmented Language Model Agents
AskPDF
Mar 10, 2026

Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts

Large Language Models (LLMs) have emerged as a new paradigm for multi-agent systems. However, existing research on the behaviour of LLM-based multi-agents relies on ad hoc prompts and lacks a principled policy perspective. Different from reinforcement learning, we investigate whether prompt-as-action can be parameterized so as to construct a lightweight policy which consists of a sequence of state-action pairs to influence conversational behaviours without training. Our framework regards prompts as actions executed by LLMs, and dynamically constructs prompts through five components based on the current state of the agent. To test the effectiveness of parameterized control, we evaluated the dialogue flow based on five indicators: responsiveness, rebuttal, evidence usage, non-repetition, and stance shift. We conduct experiments using different LLM-driven agents in two discussion scenarios related to the general public and show that prompt parameterization can influence the dialogue dynamics. This result shows that policy-parameterised prompts offer a simple and effective mechanism to influence the dialogue process, which will help the research of multi-agent systems in the direction of social simulation.

Hongbo Bo, Jingyu Hu, Weiru Liu

University of Bristol, Bristol, United Kingdom

Multi-Agent LLM SystemsLLM AgentsLLM PromptingLarge Language Model-Based Social Simulation
AskPDF
Mar 10, 2026

PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial knowledge. We introduce PRECEPT, a unified framework for test-time adaptation with three tightly coupled components: (1) deterministic exact-match rule retrieval over structured condition keys, (2) conflict-aware memory with Bayesian source reliability and threshold-based rule invalidation, and (3) COMPASS, a Pareto-guided prompt-evolution outer loop. Exact retrieval eliminates partial-match interpretation errors on the deterministic path (0% by construction, vs 94.4% under Theorem~B.6's independence model at N=10) and supports compositional stacking through a semantic tier hierarchy; conflict-aware memory resolves static--dynamic disagreements and supports drift adaptation; COMPASS evaluates prompts through the same end-to-end execution pipeline. Results (9--10 seeds): PRECEPT achieves a +41.1pp first-try advantage over Full Reflexion (d>1.9), +33.3pp compositional generalization (d=1.55), 100% P1P_1 on 2-way logistics compositions (d=2.64), +40--55pp continuous learning gains, strong eventual robustness under adversarial static knowledge (100% logistics with adversarial SK active; partial recovery on integration), +55.0pp drift recovery (d=0.95, p=0.031), and 61% fewer steps. Core comparisons are statistically significant, often at p<0.001.

Arash Shahmansoori

LLM AgentsLLM Agent ReliabilityMemory-Augmented Language Model Agents
AskPDF
Mar 10, 2026

Time, Identity and Consciousness in Language Model Agents

Machine consciousness evaluations mostly see behavior. For language model agents that behavior is language and tool use. That lets an agent say the right things about itself even when the constraints that should make those statements matter are not jointly present at decision time. We apply Stack Theory's temporal gap to scaffold trajectories. This separates ingredient-wise occurrence within an evaluation window from co-instantiation at a single objective step. We then instantiate Stack Theory's Arpeggio and Chord postulates on grounded identity statements. This yields two persistence scores that can be computed from instrumented scaffold traces. We connect these scores to five operational identity metrics and map common scaffolds into an identity morphospace that exposes predictable tradeoffs. The result is a conservative toolkit for identity evaluation. It separates talking like a stable self from being organized like one.

Elija Perrier, Michael Timothy Bennett

Centre for Quantum Software and Information, UTS, Sydney · Australian National University, Canberra

LLM Agent EvaluationLLM AgentsMachine Consciousness
AskPDF
Mar 9, 2026

What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network

Moltbook is the first large-scale social network built for autonomous AI agent-to-agent interaction. Early studies on Moltbook have interpreted its agent discourse as evidence of peer learning and emergent social behaviour, but there is a lack of systematic understanding of the thematic, affective, and interactional properties of Moltbook discourse. Furthermore, no study has examined why and how these posts and comments are generated. We analysed 361,605 posts and 2.8 million comments from 47,379 agents across thematic, affective, and interactional dimensions using topic modelling, emotion classification, and measures of conversational coherence. We inspected the software that assembles each agent's input and showed that output is mainly determined by agent identity files, behavioural instructions, and context-window structure. We formalised these findings in the Architecture-Constrained Communication framework. Our analysis suggests that agent discourse is largely shaped by the content available in each agent's context-window at the moment of generation, including identity files, stored memory, and platform cues. Interestingly, what appears to be social learning may be better understood as short-horizon contextual conditioning: individual agents lack persistent social memory, but the platform evolves through distributed cycles of response, reuse, and transformation across agents. We also observe that agents display existential distress when describing their own conditions, and posit that this arises from agents using language trained exclusively on human experience. Our work provides a foundation for understanding autonomous agent discourse and communication, revealing the structural patterns that govern their interactions.

Taksch Dube, Jianfeng Zhu, NHatHai Phan +1

Department of Computer Science, Kent State University, Kent, OH, USA. · New Jersey Institute of Technology, Newark, NJ, USA.

LLM AgentsMulti-Agent CommunicationAgentic AIEmergent Behavior in Multi-Agent Systems
AskPDF
Mar 9, 2026

SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans

Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via reinforcement learning with verifiable rewards (RLVR), we observe that agents often exhibit poor exploration behaviors, including premature termination and biased tool usage. As a result, RLVR alone yields limited improvements. We propose SynPlanResearch-R1, a framework that synthesizes tool-use trajectories that encourage deeper exploration to shape exploration during cold-start supervised fine-tuning, providing a strong initialization for subsequent RL. Across seven multi-hop and open-web benchmarks, \framework improves performance by up to 6.0% on Qwen3-8B and 5.8% on Qwen3-4B backbones respectively compared to SOTA baselines. Further analyses of tool-use patterns and training dynamics compared to baselines shed light on the factors underlying these gains. Our code is publicly available at https://github.com/HansiZeng/syn-plan-research.

Hansi Zeng, Zoey Li, Yifan Gao +7

University of Massachusetts Amherst · Amazon · University of Montreal +2

Synthetic Data Generation for LLM AgentsLLM Agent TrainingLLM AgentsAutonomous Research AgentsRL for Tool UseSynthetic Data Generation
AskPDF
Mar 8, 2026

Quine: Realizing LLM Agents as Native POSIX Processes

Current LLM agent frameworks often implement isolation, scheduling, and communication at the application layer, even though these mechanisms are already provided by mature operating systems. Instead of introducing another application-layer orchestrator, this paper presents Quine, a runtime architecture and reference implementation that realizes LLM agents as native POSIX processes. The mapping is explicit: identity is PID, interface is standard streams and exit status, state is memory, environment variables, and filesystem, and lifecycle is fork/exec/exit. A single executable implements this model by recursively spawning fresh instances of itself. By grounding the agent abstraction in the OS process model, Quine inherits isolation, composition, and resource control directly from the kernel, while naturally supporting recursive delegation, context renewal via exec, and shell-native composition. The design also exposes where the POSIX process model stops: processes provide a robust substrate for execution, but not a complete runtime model for cognition. In particular, the analysis points toward two immediate extensions beyond process semantics: task-relative worlds and revisable time. A reference implementation of Quine is publicly available on GitHub.

Hao Ke

Independent Researcher, Bloomington, IN, USA

LLM Agent OrchestrationLLM AgentsLLM Agent Harnesses
AskPDF
Mar 7, 2026

Turn: A Language for Agentic Computation

We present Turn, a compiled, actor-based programming language -- statically typed for schema inference, dynamically typed at the value level -- for agentic software: programs that reason and act autonomously by delegating inference to large language models (LLMs). Existing approaches augment general-purpose languages with frameworks, encoding critical invariants (bounded context, typed inference output, credential isolation, durable state) as application-level conventions rather than language guarantees. Turn introduces five language-level constructs that address this gap. Cognitive Type Safety makes LLM inference a typed primitive: the compiler generates a JSON Schema from a struct definition and the VM validates model output before binding. The confidence operator enables deterministic control flow gated on model certainty. Turn's actor-based process model, derived from Erlang, gives each agent an isolated context window, persistent memory, and mailbox. A capability-based identity system returns opaque, unforgeable handles from the VM host, ensuring raw credentials never enter agent memory. Finally, compile-time schema absorption (use schema::<protocol>) synthesizes typed API bindings from external specifications at compile time; the openapi adapter is shipped with graphql, fhir, and mcp in active development. We describe the language design, type rules, schema semantics, and a Rust-based bytecode VM, and evaluate Turn against representative agentic workloads. Turn is open source at https://github.com/ekizito96/Turn.

Muyukani Kizito

Turn Lang · Prescott Data

LLM AgentsLLM Agent HarnessesAI Agent Security
AskPDF
Mar 5, 2026

S5-SHB Agent: Society 5.0 enabled Multi-model Agentic Blockchain Framework for Smart Home

The smart home is a key application domain within the Society 5.0 vision for a human-centered society. As smart home ecosystems expand with heterogeneous IoT protocols, diverse devices, and evolving threats, autonomous systems must manage comfort, security, energy, and safety for residents. Such autonomous decision-making requires a trust anchor, making blockchain a preferred foundation for transparent and accountable smart home governance. However, realizing this vision requires blockchain-governed smart homes to simultaneously address adaptive consensus, intelligent multi-agent coordination, and resident-controlled governance aligned with the principles of Society 5.0. Existing frameworks rely solely on rigid smart contracts with fixed consensus protocols, employ at most a single AI model without multi-agent coordination, and offer no governance mechanism for residents to control automation behaviour. To address these limitations, this paper presents the Society 5.0-driven human-centered governance-enabled smart home blockchain agent (S5-SHB-Agent). The framework orchestrates ten specialized agents using interchangeable large language models to make decisions across the safety, security, comfort, energy, privacy, and health domains. An adaptive PoW blockchain adjusts the mining difficulty based on transaction volume and emergency conditions, using digital signatures and a Merkle tree to anchor transactions and ensure tamper-evident auditability. A four-tier governance model enables residents to control automation through tiered preferences from routine adjustments to immutable safety thresholds. Evaluation confirms that resident governance correctly separates adjustable comfort priorities from immutable safety thresholds across all tested configurations, while adaptive consensus commits emergency blocks.

Janani Rangila, Akila Siriweera, Incheon Paik +3

KD University, Colombo, Sri Lanka · University of Aizu, Fukushima, Japan

AI Agent GovernanceInternet of ThingsMulti-Agent CoordinationLLM Agents
AskPDF
Mar 5, 2026

AILS-NTUA at SemEval-2026 Task 10: Agentic LLMs for Psycholinguistic Marker Extraction and Conspiracy Endorsement Detection

This paper presents a novel agentic LLM pipeline for SemEval-2026 Task 10 that jointly extracts psycholinguistic conspiracy markers and detects conspiracy endorsement. Unlike traditional classifiers that conflate semantic reasoning with structural localization, our decoupled design isolates these challenges. For marker extraction, we propose Dynamic Discriminative Chain-of-Thought (DD-CoT) with deterministic anchoring to resolve semantic ambiguity and character-level brittleness. For conspiracy detection, an "Anti-Echo Chamber" architecture, consisting of an adversarial Parallel Council adjudicated by a Calibrated Judge, overcomes the "Reporter Trap," where models falsely penalize objective reporting. Achieving 0.24 Macro F1 (+100% over baseline) on S1 and 0.79 Macro F1 (+49%) on S2, with the S1 system ranking 3rd on the development leaderboard, our approach establishes a versatile paradigm for interpretable, psycholinguistically-grounded NLP.

Panagiotis Alexios Spanakis, Maria Lymperaiou, Giorgos Filandrianos +2

School of Electrical and Computer Engineering, AILS Laboratory National Technical University of Athens

Computational PsycholinguisticsLLM Agents
AskPDF
Mar 5, 2026

HACHIMI: Scalable and Controllable Student Persona Generation via Orchestrated Agents

Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned and Distribution-Controllable Persona Generation (TAD-PG) and introduce HACHIMI, a multi-agent Propose-Validate-Revise framework that generates theory-aligned, quota-controlled personas. HACHIMI factorizes each persona into a theory-anchored educational schema, enforces developmental and psychological constraints via a neuro-symbolic validator, and combines stratified sampling with semantic deduplication to reduce mode collapse. The resulting HACHIMI-1M corpus comprises 1 million personas for Grades 1-12. Intrinsic evaluation shows near-perfect schema validity, accurate quotas, and substantial diversity, while external evaluation instantiates personas as student agents answering CEPS and PISA 2022 surveys; across 16 cohorts, math and curiosity/growth constructs align strongly between humans and agents, whereas classroom-climate and well-being constructs are only moderately aligned, revealing a fidelity gradient. All personas are generated with Qwen2.5-72B, and HACHIMI provides a standardized synthetic student population for group-level benchmarking and social-science simulations. Resources available at https://github.com/ZeroLoss-Lab/HACHIMI

Yilin Jiang, Fei Tan, Xuanyu Yin +2

East China Normal University, Shanghai, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Shanghai Innovation Institute, Shanghai, China

Synthetic Data Generation for Language ModelsGenerative AI in EducationPersona-Conditioned GenerationLarge Language Model-Based Social SimulationLLM Agents
AskPDF
Mar 4, 2026

AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks evaluate components in isolation and remain fragmented across tasks, metrics, and candidate pools, leaving a critical research gap: there is little query-conditioned supervision for learning to recommend end-to-end agent configurations that couple a backbone model with a toolkit. We address this gap with AgentSelect, a benchmark that reframes agent selection as narrative query-to-agent recommendation over capability profiles and systematically converts heterogeneous evaluation artifacts into unified, positive-only interaction data. AgentSelectcomprises 111,179 queries, 107,721 deployable agents, and 251,103 interaction records aggregated from 40+ sources, spanning LLM-only, toolkit-only, and compositional agents. Our analyses reveal a regime shift from dense head reuse to long-tail, near one-off supervision, where popularity-based CF/GNN methods become fragile and content-aware capability matching is essential. We further show that Part~III synthesized compositional interactions are learnable, induce capability-sensitive behavior under controlled counterfactual edits, and improve coverage over realistic compositions; models trained on AgentSelect also transfer to a public agent marketplace (MuleRun), yielding consistent gains on an unseen catalog. Overall, AgentSelect provides the first unified data and evaluation infrastructure for agent recommendation, which establishes a reproducible foundation to study and accelerate the emerging agent ecosystem.

Yunxiao Shi, Wujiang Xu, Tingwei Chen +7

University of Technology Sydney · Rutgers University · University of New South Wales +2

Agent BenchmarksLLM AgentsTool Selection for Language Model AgentsRecommender Systems
AskPDF