General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockchain environments. On-chain execution is stateful, adversarial, and economically irreversible, exposing three fundamental gaps: Reactivity, Irreversibility, and Observability. We propose ChainClaw, a blockchain-native agent framework built on OpenClaw, that addresses all three gaps through a layered architecture comprising an event-driven orchestration layer, a simulation-based safety intelligence layer, and an on-chain monitoring runtime layer, unified by a cross-layer memory subsystem. ChainClaw closes the Reactivity gap via event ingestion and simulation feedback, the Irreversibility gap via a pre-execution safety pipeline with transaction simulation and action guard, and the Observability gap via an on-chain read adapter and transaction monitor. We evaluate ChainClaw on a purpose-built benchmark covering seven tasks across four categories and five dimensions. ChainClaw consistently outperforms representative baselines on both safety and task completion.
Memory-augmented VLM agents act on persistent spatial knowledge, yet that knowledge silently goes stale as the environment changes. We ask what happens when an agent must reconcile a confident memory claim with a contradicting observation, and whether current models can catch the conflict before it becomes a safety-relevant mistake. Using a dynamic FrozenLake testbed, we pair a staleness-detection task with a downstream navigation task across three closed-source models and three open-weight VLMs under both text and image inputs (1,800 detection runs, and 12,000 text-mode navigation episodes over four LLM navigators at a shared 50-seed scale). Three findings emerge. First, text solvability does not imply visual grounding: models that flag stale entries reliably from text nonetheless span vision F1 from 0.887 down to 0.067 on the identical grids, and the weakest keeps making fluent, confident decisions that ignore the image. Second, consuming stale memory without an audit is a safety liability: in our primary GPT-4o setting, an agent that trusts raw memory dies more than twice as often as the same agent given no memory at all. Third, auditing helps but does not close the gap: a transparent read-time filter removes much of the safety cost in text mode, yet even oracle stale labels bring no further significant gain on the current grid size, and when visual auditing is unreliable, filtering yields no consistent benefit. Together these results frame spatial-memory staleness as a safety failure mode and isolate reliable visual grounding and action selection under memory--observation conflict as the central open challenges for memory-augmented agents.
LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures. This is especially hazardous in safety-critical embodied settings such as automotive cockpits, where lexically correct utterances may trigger dangerous physical operations. Existing attribution methods rely on text traces alone, missing dependency structure, multi-channel evidence, and safety-aware evaluation. We introduce CockpitHAT, a hierarchical attribution framework that replaces positional windows with dependency-distance thresholds from interaction DAGs, integrates multi-channel evidence via an embodied adapter, and applies a safety-uplift to high-risk failures during confidence-weighted analyst consensus. We further release CockpitBench, a benchmark of 212 annotated failure traces spanning dialogue, vehicle-state, environmental, and memory channels, each labeled with ISO 26262 ASIL severity via three-expert consensus. On the public Who&When benchmark, CockpitHAT achieves agent-level / step-exact accuracies of 77.9% / 37.8% on the Hand-Crafted split and 86.5% / 46.0% on the Algorithm-Generated split, surpassing the text-only SOTA ECHO by up to 17.6 / 16.7 points. On CockpitBench, it attains 78.3% agent-level and 38.2% step-exact accuracy. These results establish dependency-aware, multi-channel, risk-calibrated attribution as an effective paradigm for reliable failure diagnosis in real-world embodied LLM multi-agent systems.
LLM-based multi-agent systems (LLM-MAS) solve complex tasks through specialized collaboration, but inter-agent dependencies can propagate hallucinated or malicious outputs into system-level failures. Auditor agents mitigate these risks, yet existing strategies face an efficiency dilemma: end-only auditing reviews long trajectories and final outputs, potentially weakening audit effectiveness and enlarging rollback scope, while auditing every agent each round improves detection and localization at high token cost. How can guard performance be preserved while minimizing token cost? To address this problem, we propose BRA-Audit, a budget-aware runtime auditing framework that models MAS execution as a dynamic dependency graph and formulates audit scheduling as audit-point placement under a fixed audit-call budget to minimize cumulative unchecked exposure. Its greedy scheduler prioritizes influential and long-unaudited regions, while trusted audit points enable localized recovery. Across structured coordination, complex reasoning, and open-ended tasks, BRA-Audit restores performance close to the clean setting, remains competitive with heavy guard methods and reduces end-to-end token consumption by \(17.2\%\)--\(40.6\%\).
Zhuoning Xu, Xiucheng Zhang, Hanjun Luo +3cs.MA cs.AI
Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original authorization boundaries. Existing safety benchmarks mainly study adversarial compromise, while work on constraint drift lacks controlled architecture-level evaluation. We introduce MasDrift, a benchmark of 600 benign productivity tasks across eight domains. Each task pairs required work with reserved actions. MasDrift compares single-agent, centralized, and decentralized coordination while varying hierarchy depth and peer width, measuring task completion and authorization preservation. Across generic multi-agent conditions, centralized hierarchies achieve 93.9--98.6% task completion versus 85.7--87.0% for peer networks, while unauthorized actions occur in 2.7--19.8% of tasks versus 0.6--0.8%, a gap that widens with hierarchy depth. We further compare two defenses that differ in where authorization evidence resides. One re-anchors every pending call to the original user request. The other carries an attenuated policy along the delegation chain. Re-anchoring reduces unauthorized actions in every model configuration we evaluate, at a cost of 1.6 points of pooled completion. Chain propagation blocks required work instead, forfeiting up to 36.3 points. A heterogeneous case study confirms that the failure follows from coordination rather than model strength. MasDrift exposes a centralization tradeoff and makes authorization preservation a measurable property of MAS design.
Fabio Orazio Mirto, Luca D'Agati, Giuseppe Tricomi +4cs.AI cs.MA cs.SE
Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice beyond component testing and one-shot input--output evaluation, because acceptable system behavior now depends on how decisions unfold over time and under changing environmental conditions. This survey synthesizes 257 papers spanning agent evaluation, software assurance, cyber-physical systems, runtime monitoring, and regulatory guidance in order to characterize the validation problem for agentic systems. The review is organized around a five-dimension taxonomy covering behavioral, safety, temporal, regulatory, and multi-agent concerns, and uses that taxonomy to map current approaches and expose recurrent coverage gaps. The analysis shows that behavioral evaluation is comparatively mature, while temporal validity, runtime evidence maintenance, regulatory legibility, and open-ended multi-agent systems assurance remain under-developed. Three cross-domain case studies (medical care, industrial operations, smart-mobility systems) provide operational illustrations of how the five taxonomy dimensions recur in safety-critical settings, grounded in the failure patterns documented in the reviewed literature. The paper concludes with a lifecycle-oriented research agenda centered on bounded-autonomy specifications, adversarial trajectory generation, runtime monitoring, and audit-ready evidence structures. The central claim is that trustworthy deployment of agentic AI depends on validating trajectories in context rather than assessing isolated components alone.
LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with real side effects. Current agent memory systems treat every accepted write as immediately actionable truth, so a polluted tool result, a stale update, or a teammate's half-finished note can silently drive an irreversible action. We argue that a memory write is not a belief commit. We present MemTX, a transactional belief-commit protocol. Each record carries evidence, permissions, provenance, and validity. Writes are staged inside snapshot-isolated transactions and admitted by a validate-and-commit pipeline, irreversible tool calls are gated on in-flight belief state, and retracting a belief triggers typed cascading repair of its derived records and tool side effects. Two invariants, action-safety gating and cascade-repair completeness, are machine-checked by property-based testing and bounded exhaustive enumeration of 5.5 million protocol states, with zero violations. Across five backbones from three model families, MemTX leads all eight baselines with paired-McNemar significance on four backbones and statistically ties the best baseline on the fifth and strongest, while remaining the only method with zero downstream harm on every backbone. Backbone capability does not substitute for commit discipline.
Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz +3cs.AI cs.CL
Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance. While academic work has emphasized benchmarks and algorithmic innovation, deployment raises new challenges around robustness, safety, and reliability. This tutorial brings together researchers and practitioners to explore advances in reasoning and planning, multi agent coordination, and evaluation, highlighting open challenges arising from deployment experience. Through applied case studies in pharmaceutical discovery and financial systems, we analyze common design patterns that make agentic systems successful, and discuss practical mitigation strategies for failure modes, such as verification pipelines, fallback mechanisms, and human in the loop supervision. Attendees will gain a comprehensive view of the field along with concrete design patterns, evaluation checklists, and templates for safe and reliable deployment across industries.
Chetan Arora, Andreas Vogelsang, Abbi Sharmacs.SE cs.AI
Agentic AI systems do not just predict or recommend; they plan, maintain state, and act in external environments with varying degrees of autonomy. This changes the requirements engineering problem in a specific and under-addressed way: it introduces what we call the delegated-autonomy boundary -- the set of decisions about what may be delegated to the system, under what graduated authority, with what oversight, and how control is returned. Current practices bury these decisions inside prompts, tool schemas, and runtime policies, even though they are requirements-level commitments. This paper proposes two complementary artifacts. First, an Agency Justification Record (AJR) helps teams decide when an agent is warranted over simpler alternatives. Second, an Agentic Delegation Policy (ADP) captures what must be specified for safe and effective development: purpose, authority, information, coordination, assurance, and evolution. Crucially, authority in the ADP is modelled as graduated, i.e., a tiered structure. We illustrate the framework with two contrasting examples: a safety-critical hospital discharge coordination agent and an automated code review agent.
LLMs increasingly generate workflow actions and repairs that may be well formed yet stale, infeasible, conflicting, or destructive of their own evidence. We introduce Agentic Transaction Processing (ATP), which treats generated actions as untrusted proposals until deterministic admission accepts them under an executable constraint set C. Its two-sided principle is: a proposal is not truth, and no proposal foresees every disruption. Anything may propose, but only the runtime admits and commits; unforeseen disruptions trigger bounded reactive repair whose output re-enters admission. Mnemosyne realizes ATP with an append-only transition log, effective-state projection, dependency-safe compensation, and active contract records. Under stated assumptions and relative to C, we prove four safety properties (authority separation, serial-equivalent generative admission, evidence-preserving repair, and obligation containment) and establish bounded reactive repair. Across nine safety benchmarks and a four-case Temporal SDK comparison, ATP rejects every targeted violation while admitting valid work. A matched data-size sweep measures 5.2-6.6% incremental throughput cost over the same local durable commit path and exposes local saturation. In a companion scheduling harness, local repair edits nearly an order of magnitude fewer operations than global recompute; a 12-scenario interruption stress test rejects every stale recovery candidate without losing observations or producing invalid commits. Two bounded pilots route 80 proposals from four heterogeneous LLMs through the same gate with zero invalid commits; 24 of 40 mid-execution proposals are admitted and 16 are rejected, including four explicit safety rejections.
Idelfonso B. R. Nogueira, Sigurd Skogestadeess.SY cs.LG
Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason is the difficulty of supplying narrow context to a general-purpose model and of bounding the task it is asked to perform. It is possible to hypothesise that a multi-agent reformulation under process-control principles offers a route to address those points, since control theory provides a discipline of decomposing a system into elements of contained scope, each defending one controlled variable, with conflicts resolved by structural priority: MIN/MAX selector networks for CV-CV switching and split-range (split-parallel) logic for MV-MV switching. The present work proposes such a reformulation, derived from Advanced Regulatory Control (ARC) theory. Each feedback loop in the ARC chain is mapped to one specialised LLM operator agent carrying the loop's control-theoretic context (controlled variable, setpoint, chain priority, selector kind). The chain's interaction logic (MIN/MAX selectors, override paths) is encapsulated as a single orchestrator agent. Two orchestrator variants are tested: a deterministic rule chain, and a Claude-based LLM orchestrator at a slower tier. The control principles limit each agent's task and inform how its limitations are handled. The multi-agent system inherits the safety property of the ARC chain: every constraint conflict is resolved deterministically by the orchestrator, regardless of the LLM output. Evaluated on a dairy-barn ventilation case over a 4-day mixed-season scenario, Qwen 2.5 7B Instruct operator agents running offline on a 24 GB consumer GPU at a 5-minute cadence produce auditable trajectories, each paired with an operator-voice rationale that supports a control campaign logbook.
Tool-augmented language-model agents are often evaluated by whether they select the correct tool, produce valid API arguments, and complete the requested task. However, an agent may choose the right tool and still act on the wrong external entity. For example, a request to "email Alex about the launch" may lead the agent to contact the wrong Alex, attach the wrong launch document, reply in the wrong thread, or update the wrong customer account. We call these errors entity binding failures. This paper studies entity binding failures as a distinct reliability and safety problem in tool-augmented agents. We formalize the separation between tool correctness and entity correctness, introduce a taxonomy of wrong-entity failures in enterprise workflows, and evaluate entity-aware execution mechanisms including entity-resolution preconditions, confidence-gated binding, clarification under ambiguity, and provenance tracking. In a controlled diagnostic evaluation across 60 tasks, five model backends, and six tool-use methods, all methods achieved 0.0 percent wrong-tool error, yet action-oriented baselines still produced wrong-entity actions in 24.0-26.0 percent of runs. Entity-aware methods eliminated wrong-entity actions and risk-weighted wrong-entity exposure in this setting, but reduced direct task completion by deferring under ambiguity. These findings show that safe tool use requires not only selecting the correct tool, but also reliably binding natural-language references to the correct real-world entity before action.
Eric Xing, Mingkai Deng, Jinyu Houcs.AI cs.LG cs.MA cs.RO
What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI co-scientists'', and other ``agentic" tools that promise to drive up productivity, and at the same time, ``existential" concerns such as AI escaping human control with destructive power under a speculative ``machine agency" against humans, it has become essential to clarify where automation ends and agency begins, both for building capable systems and for understanding whether and what to fear. Drawing on Descartes' grounding of agency in independent thought, and on portrayals of autonomous beings in science fiction, we survey the current landscape of AI agents, and analyze agent architectures along five dimensions: goal, identity, decision-making, self-regulation, and learning. Specifically, we argue that genuine agency requires these structures to be \emph{internalized within the system itself} rather than assembled through external scaffolding. This distinction between \emph{agentic} systems, whose competence resides in engineered workflows, and \emph{agentive} systems, whose capabilities (including social interaction) arise endogenously, defines the boundary between systems designed for prescribed tasks, and those capable of operating in the open world with true autonomy. Building on this analysis, we propose the Goal-Identity-Configurator (GIC) architecture for a general-purpose agent model, combining hierarchical goal decomposition, identity evolution, simulative reasoning grounded in a separately trained world model, learned self-regulation, and self-directed learning from both real and simulated experience. Furthermore, we share insight on the auditability, controllability, and safety of agentive systems that possess greater autonomy and ``agency", but remain under human oversight.
Sribalaji C. Anand, George J. Pappascs.MA cs.AI eess.SY
Large language model (LLM) agents are increasingly deployed in multi-agent systems where they must coordinate and agree on shared decisions. We ask whether classical resilient consensus theory, developed for deterministic agents, transfers to LLM agents that may behave adversarially. Framing LLM agreement as a Byzantine consensus game, we run controlled experiments on complete and general communication graphs. We find that prompted LLM agents fail to reach agreement that is achievable in principle: consensus can fail even in settings where classical theory guarantees that a convergent algorithm exists, and this failure persists across temperatures and horizons. At the same time, wrapping the agents with classical resilient consensus filters improves agreement. The benefit of filtering depends on how much robustness the underlying topology already provides. Our results suggest that classical resilient consensus theory is a useful lens for the safety of agentic AI.
The best agent on WorkBench in March 2024, GPT-4, completed just 43% of tasks. We revisit the benchmark in June 2026 and find that the best agent to date, Claude Fable 5, now completes 98%. Beyond this considerable progress in frontier agent performance, three things stand out. First, unintended harmful actions, such as emailing the wrong person, fell from 26% of tasks for GPT-4 to 1.9% for Claude Fable 5; capability and safety go together on WorkBench rather than trade off, so the models that finish the most tasks also do the least unintended damage. Second, the rise of open-weight models has drastically lowered costs for a performance level that was only accessible to proprietary models, while frontier costs have stayed stable. Third, while several classes of error have been eliminated, frontier models still make some basic mistakes that occasionally result in irreversible harm. We release an updated version of the benchmark with data and code quality improvements, new model scores, and analysis of agent progress on WorkBench since 2024.
Self-evolving agents improve through continual self-play and self-generated learning signals, but autonomous evolution can also cause capability degradation and safety drift. Although human feedback has proven effective for static and post-trained agents, its role in self-evolving systems remains underexplored. We introduce Agent Norm Correction through Human-like Oversight and Review (ANCHOR), an LLM-based framework that simulates human supervision and delivers feedback at various phases of self-evolution. With ANCHOR, we evaluate two representative open-source self-evolving agent systems across coding, mathematical reasoning, and safety. Our results show that even limited supervision substantially mitigates safety degradation while preserving stable performance on core evolutionary objectives. Further analysis shows that supervision over the output verification phase is the most effective for intervention, whereas increasing supervision frequency yields diminishing returns. These findings provide empirical evidence and practical guidance for designing more stable, controllable, and human-aligned self-evolving agent systems.
Autonomous science is moving from demonstration to infrastructure. Large language model agents now plan experiments, and self-driving laboratories execute them. Yet every such system rebuilds the link between the reasoning agent and the physical instrument from scratch, against fragmented vendor SDKs and standards built for deterministic software clients rather than probabilistic, goal-directed agents. Recent agent-interoperability protocols clarify two of the three edges of an agentic ecosystem (Anthropic's Model Context Protocol (MCP) standardizes the agent-to-tool edge, and Google's Agent2Agent (A2A) the agent-to-agent edge), but neither models the agent-to-instrument edge, where operations are stateful, safety-critical, exclusively owned, physically embodied, and produce measurements with units, calibration, and uncertainty. We present the Lab Agent Protocol (LAP), a protocol design that fills this gap. LAP retains A2A's peer-to-peer, discovery-first, task-lifecycle structure and adds four physical-world primitives: (i) the InstrumentCard, a signed capability and physical-limit description; (ii) first-class reservation for exclusive instrument and sample locking; (iii) a safety-fence handshake with operator-confirmation tokens cryptographically bound to a specific task and its parameters, gating hazardous and irreversible operations; and (iv) a MeasurementResult schema that makes every result physically typed (QUDT/UCUM), calibration-anchored, uncertainty-bearing, and reproducible by construction. We specify roles, a six-layer architecture, the JSON-RPC method set, the task and safety state machines, the error model, and cross-laboratory federation, and walk a closed-loop autonomous campaign through the protocol end-to-end. LAP is transport-compatible with the A2A/MCP ecosystem and encapsulates rather than replaces existing device standards such as SiLA 2 and OPC-UA.
The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the transition of these agents into trustworthy daily partners is hindered by a lack of rigorous evaluation regarding safety, efficiency, and multi-modal robustness. Current benchmarks suffer from narrow safety scenarios, noisy trajectory labeling, and limited robustness metrics. To bridge this gap, we propose OS-SPEAR, a comprehensive toolkit for the systematic analysis of OS agents across four dimensions: Safety, Performance, Efficiency, and Robustness. OS-SPEAR introduces four specialized subsets: (1) a S(afety)-subset encompassing diverse environment- and human-induced hazards; (2) a P(erformance)-subset curated via trajectory value estimation and stratified sampling; (3) an E(fficiency)-subset quantifying performance through the dual lenses of temporal latency and token consumption; and (4) a R(obustness)-subset that applies cross-modal disturbances to both visual and textual inputs. Additionally, we provide an automated analysis tool to generate human-readable diagnostic reports. We conduct an extensive evaluation of 22 popular OS agents using OS-SPEAR. Our empirical results reveal critical insights into the current landscape: notably, a prevalent trade-off between efficiency and safety or robustness, the performance superiority of specialized agents over general-purpose models, and varying robustness vulnerabilities across different modalities. By providing a multidimensional ranking and a standardized evaluation framework, OS-SPEAR offers a foundational resource for developing the next generation of reliable and efficient OS agents. The dataset and codes are available at https://github.com/Wuzheng02/OS-SPEAR.