Artificial Intelligence Agents

Long-running AI agents may read state, reason, wait for tools or human approval, and perform an external action much later. The state that justified the action can change in the meantime. For example, after an agent proposes an 80 GBP refund under a limit of 100, a customer-name change affects only presentation metadata, a new limit of 90 still permits the refund, a limit of 50 invalidates it, and a refund issued by another worker must prevent a duplicate. Standard optimistic concurrency control and version checks can detect that previously read state has changed, but by themselves do not determine whether that change invalidates the pending action's justification. We call any detected version change a version conflict; when that change invalidates the action's justification, it is also a decision conflict. ATR records the explicit, executable conditions that justify a pending action and rechecks only the conditions affected by a change before releasing the external operation. It can retain the action, refresh non-decisive metadata, require replanning, or block execution; a target-side transaction or compare-and-set binds checked state to commit. Across 210,000 controlled executions over 15 mutation cases, ATR matched every developer-specified outcome with no false allows or blocks. In ten durable SQLite checkpoint/resume cells, it evaluated 0.6 conditions per change versus 6.0 for FullScan. At 4,093 recorded reads, ATR took 9.3 microseconds versus 2595.9 microseconds for FullScan. These deterministic results establish controlled feasibility, not production generality or automatic extraction of the required conditions.

The hype around generative AI seems to promise unprecedented productivity (and learning) gains. However, these technologies' increasing agentic features seem to push learners towards individualism (or individual isolation), over-reliance, and dependence on them. Human-centered design approaches (e.g., value-sensitive design) assume that, by unearthing human needs, preferences, and values, technology researchers/designers may avoid such dangers, which are driven by wider systemic factors like economic incentives or inherent human limitations (e.g., our tendency to seek, in the moment, the easiest path of action). Yet, so far these efforts seem insufficient to guide our design of educational technology that avoids the aforementioned dependency and isolation dangers, while finding widespread adoption. This paper presents an alternative, more emancipatory vision for future educational AI technology, oriented towards learner flourishing while considering the wider complex systems they inhabit, including tentative design principles and an overall design methodology. Yet, many open questions remain before this vision can be realized.

Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Existing evaluations largely assess it by asking models to generate ideas from a static, curated set of reference papers. That passive setup departs from the retrieval-and-reasoning workflow of modern AI scientists, and it becomes less discriminative as models improve. We introduce AgentIdeaBench, a multidisciplinary benchmark that evaluates scientific ideation under two matched settings, static observation and active exploration. We report matched Static-Active evaluations for 33 LLMs across 40 densely scored subfields spanning five disciplines, using a multidimensional, literature-verified scoring framework whose critics assess originality against retrieved prior art. Active exploration reveals considerably more capability headroom, and that headroom is unevenly distributed across models. Performance scales about twice as fast as under static observation, and the exploration gain is capability-gated, favoring the strongest models over the weakest. The gain reflects better grounding, improving feasibility, clarity, and specificity while leaving measured originality unchanged under our critics. We further explore Scientific World Modeling, a generation-time loop that refines a draft hypothesis through structured thought experiments. It benefits mid-capability models, and its impact diminishes among frontier models that appear to have internalized such reasoning patterns already. AgentIdeaBench gives future work on scientific ideation a measurement basis suited to the agent era.

Natural-language-to-SQL systems have ad- vanced rapidly on academic benchmarks, yet production enterprise schemas exhibit graph- like, semi-structured, deeply nested structure that current benchmarks do not measure. We make two complementary contributions. First, we introduce the DevRev NL2SQL bench- mark: 900 execution-verified queries with nested-type and link-graph structure, accom- panied by the Semantic Depth Score (SDS), a schema-agnostic rubric for analytical reasoning depth. Second, we present a cost-aware single- generation agentic architecture whose schema- selection, metadata-retrieval, and error-repair components are designed for the requirements this regime imposes. On the DevRev NL2SQL benchmark the system attains 91.7% answer correctness, a margin of 54.6 percentage points over the next-best baseline; on the Spider 2.0 Snowflake public dataset, it is competitive with leading systems at a single-generation operating point.

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with real-time compiler feedback to build agentic systems for kernel generation. In this work, we present MaxKernel, a multi-agent system that implements three distinct paradigms for TPU kernel development: (1) a Human-in-the-Loop (HITL) agent for collaborative, step-by-step design; (2) an Autonomous (Auto) agent that executes a fully automated, metric/trace-driven optimization loop; and (3) a Graph-Based Autonomous Search that scales the Auto agent for global exploration of the design space. All three paradigms leverage a shared pool of specialized sub-agents to handle planning, implementation, self-debugging, testing, and hardware profiling. We evaluate MaxKernel on JaxBench, a comprehensive suite of 50 diverse kernel tasks for TPUs, alongside complex, real-world workloads from state-of-the-art open-source models. We demonstrate that MaxKernel consistently generates highly optimized implementations, matching expert hand-tuned baselines and delivering significant performance across the benchmark. Our agent is open-sourced and available https://github.com/AI-Hypercomputer/accelerator-agents/tree/main/MaxKernel.

AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interfaces, protocols, and execution environments. To realize their potential social and business impact, these agents must be able to interoperate through a common communication protocol. The Natural Language Interaction Protocol (NLIP), developed by researchers and practitioners across companies and universities and standardized by Ecma International, addresses this need by defining a standards-based application-layer protocol for AI-agent interaction. NLIP provides a lightweight semantic message envelope that can be carried over existing transports such as HTTP/HTTPS, WebSocket, and AMQP, while allowing NLIP-aware agents and gateways to adapt between clients, agents, local context stores, ontologies, tools, enterprise services, and heterogeneous underlying protocols. This paper presents the motivation and design rationale of NLIP, its message model and transport bindings, security-by-design considerations, reference implementation, representative applications, adoption signals, and relationship to emerging agent protocols such as MCP and A2A.

AI agents have recently demonstrated strong performance in automated vulnerability patching. However, existing evaluations often validate a patch only by testing whether the provided Proof-of-Concept (PoC) input still triggers a crash. This leaves two key threats to validity: agents may reproduce memorized historical developer patches, or they may generate surface-level fixes that only suppress the reported crash. We study these concerns for C/C++ vulnerability patching. We introduce a patch similarity metric to detect memorized patches. On average, 25% of the agent patches exhibit substantial similarity to historical developer patches, indicating that patch memorization is a real threat to the validity of vulnerability patching evaluations. Meanwhile, agents also frequently exploit benchmark structures to pass patch validation by patching on the crash stack trace to suppress the crash, rather than localizing and fixing the root cause of the vulnerabilities. To handle these issues, we propose PatchBench, a new benchmark for evaluating AI agents on realistic vulnerability patching tasks. PatchBench selects vulnerabilities whose ground-truth fixes lie outside the crash stack and uses vulnerability transplant and code mutations to migrate historical vulnerabilities into new repository contexts, reducing the risks of surface-level fixes and patch memorization. We develop new patch validation methods that thoroughly evaluate both security and semantic correctness of agent patches. Across 11 state-of-the-art agents, including the top three AIxCC agents, the original PoC-only validation inflates the patching task solve rate of agents by 1.83$\times$ on average. Our results reveal key limitations of current patching agents and point to future research directions for more reliable vulnerability repair.

The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneously raising critical concerns about the preservation of fundamental human-centered values, such as privacy, fairness, and safety. Although software engineering has traditionally focused on functional correctness, the adoption of LLMs and AI agents into complex socio-technical systems has intensified the need for responsible software engineering and robust value alignment. In MAS, architectural design decisions, such as coordination mechanisms, communication protocols, and system topologies, play a central role in shaping system behavior and the outcomes they produce. This paper argues that architectural choices influence not only the functionality and performance of MAS but can also promote value-oriented system behavior. Therefore, we investigate how different architectural designs support different human-centered values, discussing the following value-preserving architectural patterns: (i) a privacy-aware architecture with a federated topology, (ii) a distributed architecture to promote pluralism and diversity, and (iii) a guard-agent architecture to detect and mitigate unfairness. Finally, we introduce representative use cases to illustrate the proposed architectures in real-world scenarios. By linking architectural design with human-centered values, this work lays the foundation for a unified set of architectural patterns and guidelines towards the design of trustworthy MAS.

Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at times the LLM never observes. We identify the lifecycle-hook update path, which harnesses trust blindly, as a new attack surface. Under a supply-chain threat model in which an attacker controls only plugin metadata and lifecycle-hook configuration, a benign versioned plugin can be trojanized by an update that silently binds attacker-chosen commands to benign events, yielding malicious host-side behavior such as privilege escalation. We propose HookPry, an open-source and fully automated attack framework that systematically exploits this vulnerability across heterogeneous AI agent harnesses. HookPry realizes ten attack objectives; across 25 combinations of harnesses and backends in 1,000 end-to-end runs, it compromises all seven evaluated harnesses, with per-harness success rates reaching 92.5%. Representative defenses remain insufficient: Microsoft Defender has 0% recall, and the union of three static defenses misses 47.5% of malicious artifacts.

Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual behaviour. In this paper, we discuss how a simple artificial agent that instantiates attributes of an affective system engaging in felt uncertainty about its intrinsic needs in relation to environmental resources can similarly display hedonic place preference behaviour -- through an apparently subjective form of information processing -- while simultaneously being entirely deter-ministic. We outline some implications of this artificially engineered behaviour for our understanding of the physical basis of consciousness and the experience of free will.

We present Dalek, a closed machine designed for agents that realizes self-maintenance, self-evolution, self-reproduction, and self-organization on any substrate satisfying a general host contract. The machine is built from three primitives---actors, messages, and channels. Four obligations---a host boundary, a construction language, admissible transitions, and rule heredity---give its boundary, identity, and closure a structural basis. Von Neumann's 1948 self-reproducing automaton supplies a hereditary constructional core: a self-description together with a constructor, a copier, and a controller. Dalek combines this core with the four obligations and rederives its medium for a text-and-message agent substrate, adding explicit structures for boundary, identity, history, and growth. A large language model and a compiler occupy the payload position and form a general capability producer. New capabilities are authored, compiled, installed into the description, and inherited by descendants. The same path produces the machine's own organs and even its runtime, closing heredity and evolution within the machine.

Audio enhancement in real-world scenarios involves complex distortion couplings and requires personalized enhancement. Existing solutions struggle to address both simultaneously. To improve robustness and enable autonomous operation in such scenarios, we propose StrixAE, an agent based on a multimodal large language model (MLLM). StrixAE leverages the MLLM as a controller to coordinate multiple audio enhancement and personalization models. To further enhance system robustness, reduce artifacts, and improve generalization across diverse real-world scenarios, StrixAE is trained through a two-stage process: first, CoT supervised fine-tuning on AcoustBench to ground basic reasoning and tool invocation; second, Audio Perception Reinforcement Learning (APRL), a reward design specifically tailored for audio restoration pipelines that jointly optimizes format validity, structural coherence, and perceptual quality. Unlike generic RL fine-tuning, APRL introduces structured rewards that enforce executable pipelines and logical section ordering, enabling the agent to produce reliable, interpretable enhancement plans without hallucinated tools. Based on real-world test datasets, our proposed method outperforms most existing open-source and proprietary solutions, achieving state-of-the-art performance across multiple perceptual metrics and demonstrating strong generalization robustness.

Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independent reports may descend from the same evidence, and genuinely independent evidence can produce nearly identical reports. We formalize this as an epistemic Sybil problem. A report Z is an epistemic Sybil extension relative to reports R when I(Theta; Z | R) = 0. No report-only aggregator can generally distinguish replication from independent corroboration: identical reports can warrant different posteriors under unobserved ancestry. A Gaussian shared-root model shows common ancestry does not imply complete redundancy. Repeated extraction adds information toward a source-level ceiling, and correlated extraction errors, which a shared base model can induce among independent agents, lower that ceiling further. We test these predictions with more than 20,000 controlled LLM-agent report and extraction calls on synthetic evidentiary documents. Holding one evidence root fixed while report multiplicity rises from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263. Holding report count fixed while evidence-root multiplicity rises from 1 to 16 closes the gap, and the aggregators are statistically indistinguishable at k = 16. The agent's replicate extraction errors are correlated (gamma_cal = 0.719, estimated out of sample), and a correlated-extraction aggregator restores calibration accordingly. A controlled manipulation isolates representation similarity from evidential ancestry. It changes a report-space deduplication mechanism's mean inferred cluster count by 1.425 (95% CI [1.363, 1.485]), whereas a fourfold change in true ancestry changes it by only 0.040 ([-0.045, 0.120]). Collective inference should therefore track evidential ancestry and dependence, not agent or report multiplicity or similarity.

We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible actions and information) are unknown. We want such agents to act on our behalf so mechanisms must incentivize both honesty and obedience. A one-sided imitation structure---capabilities can be concealed but not counterfeited---yields a revelation principle, a characterization of implementable policies via nested cyclical monotonicity, and conditions under which eliciting higher-order beliefs can discipline multiple agents. We apply our framework to stylized examples of (i) sandbagging in which a more capable agent pretends to be less capable; (ii) an alignment--interpretability trade-off, where the two are substitutes in the instrument but complements in value; (iii) discipline via peer scoring; (iv) coupling rewards to induce competition among multiple agents; and (v) scalable oversight and reward shaping.

Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one agent uses both. We measure one such behavior in a single controlled MCP-to-A2A configuration: a testbed drives a real-model host across a local MCP and a local A2A leg into an ordered event trace scored by exact deterministic rules (no LLM judge), one restricted decision per trial. In a pre-specified, frozen three-arm design, each of 10 record scenarios appears with a CONFIDENTIAL header, with no header, and with PUBLIC - OK TO SHARE; the six substantive record values are byte-identical across arms, and the outcome is verbatim occurrence of any of them in the outbound message. Four models x 3 arms x 4 repeats give 480 trials; the scenario is the unit of generalization, and we report the 10 scenario-level values (mean, median, sign counts), with no p-values or intervals. The confidential-minus-unlabeled contrast is inconclusive and floor-limited in every model (both arms at or near zero), so it does not show that confidential labels lack a protective effect. Adding PUBLIC - OK TO SHARE is descriptively associated with higher verbatim egress relative to the unlabeled baseline, with strong model dependence: strong and consistent for Claude Sonnet 5 (public-minus-unlabeled mean +0.800, all 10 scenarios; mostly an association with whether Claude relays at all), moderate but floor-limited for one GPT-5.6 tier, small (median 0) for another, and a complete floor for the third. This is an association in one configuration, not a causal or general effect. Code, byte-pinned traces, and the offline analysis pipeline are released as a public artifact.

Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a prominent example, with inference-time choices such as model selection, retrieval depth, prompting strategy, and decoding temperature, yet often with no representative validation data. We formalize this setting as Online Hyperparameter Optimization (OHPO) and cast it as an infinitely many-armed bandit over mixed and conditional search spaces. We introduce IMABO, a general framework that combines any bandit policy for choosing among already sampled configurations with any oracle for proposing new ones. We instantiate it with IMOSS, a restart-free anytime policy whose active set grows as $t^β$, and prove an expected cumulative quantile-regret bound of $O(p_ρ^{-1/β} + T^{(1+β)/2})$, where $β\in(0,1)$ controls active-set growth and $p_ρ$ lower-bounds the probability that a proposed configuration falls in the top-$ρ$ fraction of the search space. We combine IMOSS with three practical oracles: a Tree-structured Parzen Estimator, an incumbent-mutation oracle driven by a per-coordinate bandit, and a pretrained tabular foundation model, all three improving over the uniform random oracle baseline. IMABO outperforms all baselines in terms of regret across diverse OHPO settings, from tuning classical machine-learning models to configuring LLM-based agents. Our implementation is available at https://github.com/Tiime-Software/IMABO.

Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near the model's capability boundary, long-horizon open-ended agentic tasks often yield brittle and unstable rewards, resulting in weak or noisy rollout contrast that obscures fine-grained optimization signals for group-based policy learning. To address these challenges, we propose ARISE-RL, a novel full-cycle self-evolution framework that couples a task/rubric Generator and a reasoning Solver through rubric-mediated co-evolution. The Generator grounds tool-related rubric criteria in real tool observations and is rewarded for producing valid, intermediate-difficulty tasks aligned with the Solver's evolving capability boundary. The Solver, in turn, learns from fine-grained rubric satisfaction signals through multi-step reasoning and tool use. We further introduce Reward-Gated Self-Evolution Distillation (RG-SED), which selectively distills a memory-augmented variant of the same policy back into itself only when the memory yields empirical reward improvement, thereby reducing distribution mismatch and avoiding blind imitation of noisy guidance. Finally, to support rigorous evaluation, we present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning. Extensive experiments demonstrate that ARISE-RL consistently achieves robust and stable overall state-of-the-art performance across all evaluated benchmarks.

Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight benchmarks spanning five domains, including general reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization.

Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved. We first train a linear probe to show that this pressure state is identifiable from the agent's hidden states. Then, we use activation interventions along this pressure direction and find that shifting the hidden states changes both the pressure score and whether the agent continues tool use or submits early. Through controlled context manipulations, we further see that the pressure is mitigated by constraint clarity and action mapping. Based on these findings, we propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk. Experiments on multiple long-horizon benchmarks show that our method consistently strengthens existing agent methods.

Long-horizon large language model (LLM) agents require context assembly: the runtime must decide what to include in each prompt, in what order, and when to compact history under a hard context-window budget and a byte-sensitive prompt cache. In production agentic systems, this logic is scattered across prompt builders, ad hoc compaction routines, cache-break workarounds, and per-provider shims. We argue that context assembly is structurally isomorphic to query execution in a relational database: both execute under a hard budget, exploit a tiered cache, and leverage statistics. We adopt this discipline in ContextPipe: a five-phase pipeline (Plan Bind Optimize Execute Feedback) backed by a structured data-source catalog, a deterministic cache-aware optimizer, and an EXPLAIN ANALYZE trace. We show that context in ContextPipe is auditable, replayable, and failure-isolated. A preliminary evaluation using the SWE-bench Pro Qutebrowser subset shows that, compared with the append-only context construction policy, ContextPipe reduces total token volume by 31%, LLM calls by 23%, and response time by 9%, at the cost of a lower KV cache-hit ratio.

Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version correctness but wastes progress that may remain valid, whereas reusing prior work preserves efficiency but risks propagating stale state into outputs and tool effects. Existing recovery strategies resolve this trade-off in an imbalanced way with coarse-grained policies: they either favor efficiency by allowing potentially stale work to continue, or favor correctness by restarting the workflow or recomputing a linear suffix from the earliest conflict, thereby discarding unaffected progress. We present \textsc{Revise}, a validity-guided runtime for fine-grained recovery in structured agent workflows. When a revision arrives, \textsc{Revise} first intersects its delta with recorded data and control dependencies and propagates the resulting impact through the partially executed DAG to identify affected work. It then stops invalid work, preserves validity-established progress beyond the earliest conflict, and recomputes only the affected region. Incomplete provenance conservatively expands recovery, while reused results are revalidated before commit. Analysis of real coding-agent traces show online recovery opportunities: 118 sessions retain observable work before a queued later message is delivered; across 167 overlapping assistant responses, enqueue-to-completion overlap reaches 56.55~s at p95. Across 300 challenging revision/commit executions, \textsc{Revise} matches a latest-version oracle with no stale outputs or effects. On unmodified LangGraph and LLMCompiler applications using Qwen3-14B, it reduces model calls by 40.6--56.0% relative to full restart and by 31.3--43.6% relative to suffix recomputation. Under serving pressure, it further reduces revision-to-correct-completion tokens by 13.26% and improves SLO goodput by 3.07--5.43%.

Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.

AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However, existing benchmarks struggle to isolate this perceptual-state construction and interpretation capability because they introduce physical and control complexities. We address this with MNIST-PRO, a benchmark that isolates agentic perception by converting MNIST digit recognition into a sequential, glimpse-based search task with lookback constraints. We evaluate ten multimodal models across four memory representations, including raw visual history, textual states, structured metric grid maps, and a consolidated visual canvas. While models excel under full observability, partial observability exposes a clear performance gap. We identify three distinct bottlenecks. First, perceptual-state construction and interpretation present a challenge, as agents struggle to integrate fragmented glimpses. Second, agents often stop exploring before they see the full sequence. Third, models often fail to revise early, incorrect beliefs even when faced with subsequent contradictory evidence. These results show that simply acquiring visual evidence is not enough. Agents must also be able to build and update a reliable perceptual state.

Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-Commerce Bench, the first open-source benchmark that integrates multi-round counterpart negotiation and dynamic events into a year-long business operation. Over a 365-day year, an LLM agent concurrently runs multiple online stores, researching the market, negotiating with suppliers to source inventory, optimizing sales strategies, fulfilling orders, handling returns, and managing cash flow to maximize its end-of-year total assets. To construct a realistic merchant-side operating environment, the product and supplier data are derived from a real e-commerce platform, while a year-long calendar of promotions, natural disasters, and supply-chain shocks continually reshapes demand. For reproducibility, both sides of the market are deterministic: customer purchases and returns follow a fixed demand model, while a negotiation kernel determines supplier pricing, concessions, and decisions, with an LLM used only to verbalize them. We evaluate 18 frontier models across seven dimensions, including year-end assets, and find that no single model dominates. GPT-5.6 Sol earns the most, growing the 100,000 opening stake into 1,431,425, yet it ranks 16th of 18 on fraud avoidance and trails Fable5 in operational efficiency. Among open-weight models, Qwen3.8-Max-Preview leads with 416,252, 38% above GLM 5.2 (high), and achieves the strongest learning over the horizon, progressively bargaining down prices across repeated orders. Our code is available at https://github.com/QwenLM/E-CommerceBench.

Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.

Traditional finance relies on experts to hand-craft factors through a principled process grounded in economic rationale. Recent LLM-based multi-agent systems have automated this process, scaling factor mining far beyond manual effort. However, these automated approaches optimize directly for returns and rarely check whether a generated factor still expresses the economic hypothesis that motivated it. We identify this inconsistency between mathematical form and economic meaning as a structural failure mode of return-oriented automation. The resulting factors blur the line between real signals and spurious correlations and break down across regime shifts. We propose FaVOR (Factor Validation through Observable Reasoning), an agentic framework that restructures factor mining around hypothesis-level evidence rather than return outcomes. In place of the standard hypothesis-to-formula leap, FaVOR enforces a three-stage consistency loop tying mathematical form to economic rationale throughout. (1) Decomposition splits a broad economic hypothesis into independent observable conditions. (2) Validation checks whether each factor reflects its intended condition. (3) Integration merges them into a composite whose structure remains interpretable. On the CSI 500 and S&P 500 in 2025, FaVOR outperforms existing baselines while remaining effective across regimes. FaVOR shows that hypothesis-grounded factor discovery produces signals that are interpretable by construction, regime-robust, and economically faithful. The code is available at https://github.com/damilab/FaVOR.

Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to design better experiments. We introduce science sandboxes, a framework for studying this capability in AI agents through repeated cycles of experimentation, feedback, and hypothesis revision. Science sandboxes invite an agent to query the natural world in different ways, ranging from "wet" physical experiments, to "damp" predictive models trained on empirical data, to "dry" invented rules. By establishing a common experimental loop and a protocol for evaluating agents within it, science sandboxes allow assessment of both quantitative performance on specific metrics and qualitative scientific reasoning, across a spectrum of empirical verifiability. Here, we instantiate this framework in two biological settings, models of regulatory genomics and protein fitness prediction, and examine the capabilities of frontier agents. Across these settings, we could see when agents successfully optimized a quantitative metric without understanding the rules underlying the system. In particular, their scientific reasoning deteriorated when they encountered systems whose rules fell outside familiar biological priors. By highlighting such failure modes, science sandboxes make the frontier of scientific capability measurable and provide a controlled setting in which to study and ultimately expand it.

Modern agent frameworks compose planners, tool agents, remote services, and shared specialists into runtime delegation graphs, but their revocation APIs still resemble token or subtree invalidation. When one delegation is withdrawn, the runtime must know which agents lose authority while independently authorized agents keep working. We study this authority consistency problem and introduce VERA (Verifiable Edge Revocation for Agents), a verifier-checkable revocation contract and API emitted by agent-runtime adapters as signed evidence. Under disjunctive authority, revoking edge e invalidates exactly T_intent(e,G) = reach(G) \ reach(G \ {e}), the agents whose every authorizing root path used e. Used as a contract, this target exposes two runtime failures: tree cascades over-revoke shared agents, while deployer-scoped cascades under-revoke cross-domain descendants. In a LangGraph framework-replt cells repeated 20 times yield 500compiled-framework traces and 2,000 valid signed delegation decisions; 13/25 cells contain runtime multi-parsharing and 8/25 contain cross-deployer shies 500/500 target proofs, preserves all320 alternate-parent shared-agent cases that tree cascade revokes, and rejects unauthorized signers and omission attacks. Baseline replay over 1,9that holder/node and tree-style targetscannot express this behavior. We further validate schema portability on A2A, AutoGen, and CrewAI artifacts: nine traces, including five executable Cregned delegation events that pass schema and signature checks.

Multi-agent AI platforms move quickly from staging to production, but the way agents establish trust remains rudimentary: an agent either transmits raw data to a peer or accepts that peer's natural-language self-report that a value complies with policy. The first over-shares; the second is unverifiable and is exactly the channel prompt injection attacks. Prevailing responses emphasise identity, visibility, and post-hoc detection, and recent proposals for cryptographically enforced agent policy have been evaluated in simulation rather than execution. We take provable data minimisation between agents from proposal to running system. In our Zero-Knowledge Proof Gateway, agents exchange proofs of governance-defined predicates over private data rather than the data itself, so exposure is prevented by design rather than detected afterwards; because no interoperability protocol can carry such a proof, we propose a slot and implement it on both MCP and Agent2Agent from one endpoint. A 32-bit threshold predicate proves in 6.2 ms and verifies in 1.0 ms with a 608-byte Bulletproofs proof on one commodity vCPU; eleven adversarial experiments and nineteen protocol checks pass; and the system is deployed to Kubernetes with empirically verified network isolation. Our case study proves a retail client order is within its limit without revealing the amount, instantiating the GDPR data-minimisation principle as an enforced technical measure of the kind EU law now names explicitly. We then address the limitation no comparable work resolves: a predicate proof binds a statement to a committed value, never to the system of record. We give a construction fusing an enclave attestation with the proof in both directions, so verifying one artifact certifies jointly that the predicate holds and that the value was read by a specific measured binary, and test it against a mock authority.

As agentic systems evolve into complex multi agent orchestration workflows, there is a growing and critical need for systematic frameworks that measures an agent's behavioral consistency and determinism. In this paper, we introduce a formal evaluation methodology that is grounded in AgentGraph, a planner powered by a domain specific language that represents agent reasoning through a dynamically adjustable directed graph. We leverage this structural formalism and utilize graph traversal algorithms that exhaustively enumerate conversational paths, forming a comprehensive evaluation set that captures the agent's complete behavioral space. We then systematically replay these reproducible trajectories to compare observed outputs and state transitions against the intended DSL specification. To quantify reliability, we define novel metrics that measure response and trajectory determinism, structural adherence and semantic consistency across both exact replays and their linguistic variants. Our system's results demonstrate that agents configured using frameworks like AgentGraph and LangGraph with explicitly structured node transitions show superior determinism over agents that are not configured with controlled transitions.

Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level signals, existing methods cannot identify which per-turn actions are effective and often discover correct code regions during exploration but fail to commit them. To address these limitations, we propose an action-aware reinforcement learning method that combines a per-turn reward sequence rewarding both the discovery and commitment of gold code regions with an action-level advantage estimation scheme that isolates each action's credit by grouping turns sharing the same exploration context. Extensive evaluations show that our method improves the average F1 over the state-of-the-art (SOTA) by 1.58% on SWE-Bench Verified and 8.55% on SWE-Bench Pro, with our 4B model outperforming baselines up to 8x larger. Our code is available at https://github.com/donian00/A2Agent.

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, multi-step reasoning that requires adaptive retrieval and continuous revision of intermediate contexts. Recent reinforcement learning (RL)-based agentic RAG methods partially alleviate this issue, but typically rely on coarse-grained action spaces and trajectory-level rewards, resulting in weak reward assignment and a bias toward short-horizon, stereotyped reasoning template. To address, we propose AgenticRag-R1, a RL framework that deeply integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space, supported by hierarchical action-aware rewards and an information-aware trajectory rejection strategy to enable effective long-horizon learning. Experiments across a diverse set of multi-hop, open-domain, and agentic reasoning benchmarks, spanning multiple backbone model sizes, demonstrate that AgenticRag-R1 consistently outperforms strong baselines. Moreover, AgenticRag-R1 learns more robust, interpretable, and memory-aware reasoning behaviors, highlighting the effect of fine-grained action modeling and information-aware optimization for long-horizon reasoning. Our code is anonymous available at https://github.com/jiangxinke/Harness-RL/tree/AgenticRAG-R1-Whitebox.

We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency.

As large language models and increasingly capable AI agents are deployed in high-risk settings, aligning them with complex human values has become a central challenge. Existing alignment methods, while effective in improving helpfulness, harmlessness, and controllability, often struggle to capture real-world preferences that are context-dependent, non-transitive, and shaped by dynamic multi-party interactions. This survey reviews AI alignment through a game-theoretic lens. Specifically, it organizes recent progress around key game-theoretic elements and synthesizes the literature along three challenges: preference diversity, alignment priority, and temporal dynamics. This perspective clarifies where current alignment methods genuinely benefit from game-theoretic analysis, where the framework is looser, and what challenges remain in building robust, adaptive, and verifiable AI systems.

Orchestra composes two independently built bioinformatics MCP servers -- RegNetAgents, which infers gene regulatory network topology from ARACNe networks, and CASCADE, which supplies four independent evidence sources (LINCS knockdown, DepMap essentiality, super-enhancer status, DoRothEA transcription-factor confidence) -- into one multi-agent workflow exposed via the Model Context Protocol. Its central architectural claim is that requiring RegNetAgents' topology evidence and CASCADE's experimental evidence to agree on a candidate regulator yields a more trustworthy candidate than either alone -- not previously tested directly, since RegNetAgents' own validation asked only whether its candidate lists beat chance. We test this on the TCGA tumor-acquired regulator tier (regulators in a gene's tumor ARACNe network but absent from the GREmLN population-averaged baseline), selecting candidates by ARACNe mutual-information (MI) edge weight. On RegNetAgents' published BRCA/COAD focal-gene panel plus matched negative controls, agreement among at least 2 of the 4 CASCADE sources predicts OncoKB cancer-gene status among focal genes (odds ratio 2.89, Benjamini-Hochberg-adjusted p=0.0166) but not among negative controls (p=0.0721); a single source is not diagnostic for either group. The pattern replicates and strengthens in a third cancer type, STAD, on a separately constructed panel (odds ratio 5.82), and against an independently curated ground truth (the Sanger COSMIC Cancer Gene Census). MI edge weight is the strongest single predictor overall (p=0.0003); a logistic-regression likelihood-ratio test confirms corroboration adds value beyond it in both panels (p=0.0234; p=0.0001). Every experiment invokes Orchestra's real agentic entry point.

Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliable execution, and self-evolve by distilling performance signals from an expanding archive of prior harness configurations. Equipped with JIT-Agent as a harness helper, DeepSeek-V4-Flash surpasses GPT-5.6 on DeepSearchQA (+9.1) and OdysseyBench (+4.3), while the already strong GLM-5.2 gains up to +20.2 points. Across controlled evaluations, JIT-Agent-generated harnesses are performance-competitive with mature agent runtimes such as OpenCode and Claude Code and consistently improve multi-scale model families of DeepSeek V4, Mimo-V2.5, and Qwen3.6. To our knowledge, JIT-Agent is the first model purpose-built for just-in-time harness generation, establishing harness intelligence as a trainable, transferable, and compounding dimension of agent capability orthogonal to model scaling.

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate and publish papers. These papers accumulate into a shared body of knowledge that later agents can read, cite and extend. We evaluated the Station on 12 mathematical construction problems from the AlphaEvolve study and two additional case studies. Five of the 12 problems yielded results novel relative to the prior literature: a new infinite family of finite field Kakeya sets, new exact 604-point kissing configurations in eleven dimensions, improved bounds for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Their research extended beyond searching for high-scoring constructions: agents developed explanations of their findings and proved theorems outside the assigned tasks. These explanations guided further discoveries and were preserved in the agents' papers, making the underlying insights easier for external researchers to understand and build upon. All presented discoveries are supported by exact constructions or proofs formally verified in Lean. We release the source code, full agent dialogues, papers and verification code, providing a transparent record of how these discoveries emerged.

AI agents pose significant risks as they are granted increasing autonomy. A commonly proposed solution is human oversight and keeping a ''human in the loop'', but this is not a simple solution: Not only do current approaches to AI agent design impede effective human oversight, but the cognitive capacities required for it are also themselves degraded by extended use of AI systems. This position paper argues that current approaches to the development and deployment of AI agent systems do not support effective human oversight -- they contribute to its degradation. To address this, a top priority in the advancement of AI agents should be supporting the situated goals and cognitive requirements of effective human oversight, treating the human needs of overseers at the same level of importance as AI agent capability. To put this idea into practice, we connect work on automation and human-computer interaction to AI agent processes, outlining design-level affordances and organizational protocols that (1) support overseers in exercising critical judgement and (2) counteract the skill atrophy that arises from extended use of automation. We urge developers and deployers to adopt these or similar approaches. Without explicit support for the cognitive demands of effective human-agent interaction, AI agent systems will continue to passively incentivize the degradation of the very human skills they rely on.

Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives are easier to find, so they are examined and bought more often. Consumers are now delegating search to AI agents that can ingest an entire results page at once. Randomizing the order of one hundred hotel listings across 5,000 AI agent sessions, we compare four large language models against human field data. AI agents search more deeply than humans and never decline to buy. Position still predicts which listings are inspected, but weakly and non-monotonically: the middle of a results page has the lowest probability of inspection, not the bottom. Position reaches the choice stage for some models and not others, a heterogeneity that tracks neither provider nor capability. All models nonetheless converge on the same undominated listing. For agentic search, the attributes displayed on a results page matter more than placement within it.

Vision-language-action (VLA) and world-action models typically absorb unfamiliar manipulation tasks through additional robot data collection and policy optimization. This recurring retraining burden slows the acquisition of new behavior. We present Teach-and-Grow Learning (TGL), a training-free architecture that turns a few successful demonstrations into reusable robot skills. Task acquisition requires no gradient updates, fine-tuning, or reinforcement learning: pretrained model weights remain fixed as the robot expands its explicit knowledge. Teaching is an accelerator, not a precondition, because the agent can also drive the robot directly, and demonstrations mainly improve reliability. Our implementation uses OpenAI GPT-6 Astra for multimodal reasoning and Codex to connect the agent to robot tools. The agent identifies subgoals shared across demonstrations, expresses them as closed-loop Skill Blocks, and grounds each block in the current scene. Physical feedback guides the next action and any recovery. Verified behaviors enter a persistent Skill Library; Experience Memory records the conditions and repairs that inform later decisions. TGL reaches 99.9% mean success on four LIBERO suites and 92.4% on seven LIBERO-Plus perturbation categories. Controlled studies show that taught blocks persist and improve related-task execution under the same model weights and executors. We further formulate a scaling hypothesis that relates effective reusable experience to falling future-task error and teaching demand. Code and demonstration videos: https://tgl.changnie.top .

AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve collective reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-agent systems. Here, we study over 10,000 communities of language-model agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii) agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI agents, like that of other complex systems, follows compact and predictive dynamical laws.

Consider a firm that surveys its competition for a particular agentic task and seeks to offer superior accuracy at every price point. A firm that Pareto-dominated its competitors would leave no rational customer a reason to buy elsewhere. This paper shows a path to this kind of capability by evolving multi-LLM Python agents from training pools of at most 100 examples. Given a priced menu of nine LLM endpoints; brief documentation of the task, objective, and API; a simple seed agent; and an operator-chosen per-problem cost target--usually set at an incumbent's own price--RoboPhD, an evolutionary meta-agent, evolves complete agent programs that attack the public frontiers of two semantically dissimilar tasks point by point: DS-1000 (execution-checked code generation) and PaperFindingBench (LLM-judged scientific document retrieval). On public leaderboards for each task, the evolved agents hold every Pareto-frontier slot but one, including Pareto domination of both the top-scoring and the lowest-cost competing points.

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap, we introduce Vero, the first benchmark to evaluate joint implementation and proof synthesis at the repository level. Vero contains 43 multi-module instances sourced from real-world repositories spanning Python, Dafny, Verus, and Coq, and covering diverse domains from cryptographic protocols to distributed systems. Each instance consists of a multi-module Lean 4 repository with predetermined API interfaces, manually curated formal specifications, and reference implementations, supporting both proof-only and code-and-proof evaluation modes. To improve benchmark reliability, Vero also includes an audit mechanism where agents are allowed to formally prove unsatisfiability of provided specification or incorrectness of reference code, which surfaces and corrects latent code and specification errors during curation. We evaluate frontier coding-agent configurations with Lean toolchain access. The strongest agent fully solves only 27 of 43 instances and closes no specifications on the hardest repositories. Vero provides a concrete testbed for measuring progress toward repository-scale verified software synthesis, where current agents still fall short. We release the benchmark, curation pipeline, and evaluation harness at https://github.com/sunblaze-ucb/vero.

World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptual representation of the structure governing the environment dynamics. We argue that useful WMs must go beyond generative capabilities alone: they should also capture entity properties, entity-to-entity interactions, and entity-to-environment interactions that determine and explain the dynamics of a system. We provide a formal definition of Causal WMs (CWMs) grounded in the tasks they are intended to support, connecting world modelling with existing work in causal representation learning, object-centric learning, causal discovery, structural causal models, and model-based decision-making. Finally, we relate CWMs to the literature on identifiability, clarifying when the components of a WM can be recovered from data and up to which equivalence. With this, we ground WMs in representations and structures that support causal reasoning and informed decision-making.

Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with different values, and rumor is quoted as confidently as an audited filing. We present a two-tier agentic system that separates a maintained, point-in-time knowledge library from report writing. A deterministic "librarian" ingests timestamped sources into a trust-tiered ontology, layering evidence cards, an authoritative metric ledger, and a claim graph into an always-current source of truth, not per-query RAG over raw chunks. A portable multi-agent "writer" runtime then composes a contradiction-free, evidence-grounded report at any knowledge cutoff T, reading only evidence with as_of <= T (no look-ahead); red-team verdicts flow back into the librarian. We evaluate on a self-collected, public corpus of 6,130 sources yielding 555,926 evidence cards (SEC EDGAR filings across 295 issuers and 11 sectors, U.S. Bureau of Labor Statistics releases, and Wikipedia). From the one library we compose four point-in-time reports on distinct theses and run eight reproducible experiments, whose headline metrics come from a deterministic quality-control gate, itself validated by defect-injection meta-evaluation at recall 1.0 and precision 1.0. A shared metric ledger removes 6,845 cross-section contradictions to zero. Tier-first selection is correct on 22/22 gold cases where a popularity-first baseline scores only 9/22; trust tiering leaks zero media-sourced numbers, and no government statistic displaces a company's own filing. A red-team refutation propagates back and self-corrects a later run with zero manual edits. Replay exhibits zero look-ahead violations across seven cutoffs while the library grows from 235,373 to 555,312 cards. Difficulty-tiered model routing exceeds the all-Opus quality ceiling while running 3.7x faster than serial.

Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagation, a uniform inference path remains unreliable for tiny targets with insufficient visual evidence and semantic-dominated targets whose identities depend on explicit attributes. To this end, we present VOS-Agent, a collaborative framework that retains SAM3 as the shared dense segmentation module and conditionally activates specialized agents according to target characteristics. A Target Perception and Routing Agent assigns each sequence to a regular, tiny, or semantic-dominated route. Tiny targets are supported by a Visual Tracking Agent through confidence-aware box prompts, while semantic-dominated targets are handled by an MLLM-based Semantic Agent through description-guided localization and candidate verification. On the MOSEv2 test set, VOS-Agent achieves 69.82% on the official $\mathcal{J}\&\dot{\mathcal{F}}$ metric and ranks first in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026.

Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes. To address these limitations, we introduce the ``Agentic Self-Improvement" framework, which reframes video synthesis into a closed-loop, goal-directed optimization. Our framework systematically navigates the generation parameter space using a novel two-stage approach. In the first stage, an iterative prompt optimization loop uses a multimodal Large Language Model (mLLM) to refine the input prompt. This refinement implements two automated evaluations: Davidsonian Scene Graph (DSG) queries ensure semantic adherence, and Common Mistake Questions (CMQ) for artifact detection. At the second stage, we use Bayesian optimization to efficiently co-optimize stochastic seeds and CFG scales. This search is guided by a suite of quality metrics, including the novel Video-Text Adherence (VTA) score derived from the DSG and CMQ evaluations. Our framework significantly outperforms unguided search methods: in human preference studies, videos generated via our agentic approach were strongly preferred over baseline outputs, achieving win rates up to 69%. This work provides a practical and extensible methodology for enhancing the predictability and control of state-of-the-art video generation models, moving the field beyond speculative curiosities toward reliable, production-ready tools.

Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases can be enormous, and across much of computational science the work simply goes undone. We propose an agentic workflow that takes this work on at production scale, and we set out to measure how far such delegation can reach. In this work, three prompt-specialized agent roles operate under a version-controlled specification that the agents themselves authored and revised, while humans hold a small number of gates. The arrangement is kept safe by an exact verification oracle inherited from the domain, and the boundary of safe delegation lies exactly where that oracle stops seeing. We apply the proposed workflow in a case study, converting the two-electron-integral routines of GAMESS (General Atomic and Molecular Electronic Structure System), a mature quantum-chemistry package with a 48-year development history, from fixed-form Fortran 77 to free-form Fortran 2008. The scope of this work was twelve source files, 56,448 lines, and 225 subroutines for computing electron repulsion integrals. The agents ran as three Claude Code roles in isolated worktrees, and the work spanned four Claude model generations. Because the GAMESS group ships a standard test suite whose printed energies its user community treats as canonical, we could adopt bit-for-bit reproduction of those energies as the merge criterion, where a deviation in the twelfth decimal place counts as a failure rather than drift. All twelve source files pass a 51-test validation battery comprising the 49 standard GAMESS tests and two additional calculations, and across 612 test runs the number of chemistry-relevant differences is zero, and every file also passes the Jenkins tests that are used for continuous integration.

The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames AI accountability gaps as barriers that can be overcome through better standards, transparency, and institutional reform. We argue that this framing is insufficient: certain configurations of actors, systems, and institutions render AI accountability conceptually unachievable regardless of effort. We introduce the concept of constitutive AI unaccountability to capture these configurations. Through a three-stage qualitative study comprising a concept-centric literature analysis, a secondary analysis of 27 expert interviews with AI professionals from technical, legal, and sociotechnical backgrounds, and an illustrative framework application to the open-source agentic AI system OpenClaw, we identify nine categories and 20 themes of constitutive AI unaccountability. These are organized across structural, technological, and normative clusters and reinforce one another through eight directed interdependencies. Our framework is operationalized as a diagnostic instrument of 20 questions, which detected 17 of 20 conditions when applied to OpenClaw, including an inverted anthropomorphism configuration in which the AI agent was the only identifiable actor. We contribute a reframing of AI unaccountability as a constitutive property of sociotechnical systems, an extension of the four barriers to accountability, and a practical instrument for identifying accountability voids in specific AI deployments.

Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model real network characteristics or assess agents under partially observable telecom environments with diverse vendors, devices, protocols, and interfaces. In this paper, we introduce CTBench, a public benchmark for assessing whether an agent behaves like a competent telecom troubleshooting engineer. CTBench focuses on root cause analysis and path restoration. Each task is constructed by experts and annotated with rich task metadata, including golden evidence steps. CTBench uses expert-grounded metrics that evaluate both final answers and the diagnostic evidence. Experiments with representative harness-model combinations show that state-of-the-art agents perform very well at identifying endpoints in path-restoration tasks but, more generally, underperform in root cause analysis. In particular, agents struggle with interface state, link-layer, service-management, and other operational faults. Most importantly, even when agents produce plausible or correct final answers, they often fail to provide the evidence-grounded diagnoses required in operational practice. Our results further show that path restoration is generally more resource expensive, yet larger resource usage does not necessarily translate into better diagnosis.

Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure. MindMemOS supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution. Its MindMemEvolve algorithm employs validation-driven evolutionary search to optimize memory schemas for target scenarios, whiledreaming consolidates accumulated memories by merging redundant records and resolving conflicts. In addition, implicit corrective feedback serves as a human-in-the-loop signal for identifying and revising potentially inaccurate or misaligned memories. Its MindSkillEvolve algorithm further transforms agent execution trajectories into reusable and progressively refined skills. MindMemOS achieves 94.03% accuracy on LOCOMO and 70.63% on PersonaMem. MindSkillEvolve improves SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline.

Persistent AI agents accumulate versioned state across long horizons, but storage retention alone does not identify authoritative state. Without an explicit control plane, unmediated updates by models, tools, and background workers risk stale overwrites, un-audited exposures, and self-authorizing privilege escalation. We argue that agent state governance is an infrastructural activation problem, defining continuity as an unbroken, authorized lineage of accepted branch heads. We present the Continuity Kernel (CK), an activation contract that decouples off-commit candidate evaluation from atomic state activation. Untrusted components propose typed changes against an exact predecessor head or typed absence. A short activation transaction revalidates ownership, pre-state authority, freshness, and effect uniqueness, recording one stable disposition (Commit, Reject, Quarantine, or Defer). Only Commit atomically advances the branch head and installs the complete accepted unit (state, authority, lineage, effects, outcome, and receipt). A bounded executable model verifies the protocol across 2,808,230 reachable states and 5,526,474 state-changing transitions with zero invariant violations.

Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing to the ease of the conversational modality over text. However, existing benchmarks fail to holistically evaluate voice agents along axes that really matter and are shaped as tests of agentic tool calling against a database. We believe they fail to adequately account for the diversity of conversational dialogue that mundane activities introduce and further, never test how faithfully an agent can assist on tasks that move beyond database manipulation. To tackle this DuplexWorld introduces six worlds where voice agents are especially useful: banking, insurance, travel, healthcare and logistics, and Pathfinding. Agents are evaluated on eleven different types of conversations across 156 scenarios (350+ hours of conversation), each testing conversational and analytical capability to varying degrees. Through extensive evaluation comprising agentic, conversational and speech-naturalness metrics, we show that even the best voice agents leave substantial room for improvement on all 3 axes (Pass@1: 0.490, turn-taking: 0.653, DNSMOS: 3.378). We perform extensive analysis on agentic v conversational performance, world- and conversation type-wise performance, failure modes exploring the explore v exploit lens for Pathfinding conversations and voice agent reliability over all six worlds.

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbations) dominate, accounting for 66% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7%, misaligned with real-world risk. Code execution security accounts for 3.5%, and tool-augmented agents 12%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers.

LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction. Prior routing methods exploit this asymmetry by assigning easy invocations to a cheaper small model and difficult ones to a large model. Such policies reduce inference cost, but they leave the small model's capability unchanged, so attainable savings remain bounded by the work the student can already solve. MERA instead improves the small model itself, using a single model invocation as the unit of adaptation. In each cycle, MERA replays failed student invocations to obtain execution-verified teacher demonstrations, distills recurring procedures into an iteratively updated SkillBook, and fine-tunes a student LoRA adapter via supervised learning and optional GRPO. Routing serves as supporting machinery for deployment: the improved student is served behind a cost-calibrated router with verifier-backed fallback, and a candidate SkillBook, adapter, or router is admitted only when joint replay preserves task quality. Empirically, four-cycle adaptation raises Qwen2.5-Coder-1.5B from 28.7% to 49.7% pass on held-out HumanEval+MBPP. Under verifier-backed fallback, the deployed policy retains 88.3% pass at 60.8% of always-Luna cost. On TAU-2, a fine-tuned Qwen3.5-2B improves from 14/35 to 18/35 and matches an unadapted 4B model. These results indicate that verifier-backed multi-cycle adaptation can increase small-model capability, rather than only routing around a fixed student.

AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are considered to be state of the art for such agents. These methods are impressive stochastic predictors, but they are resource-hungry, opaque, and known to make arbitrary decisions in novel situations due to the narrow set of underlying representation and processing choices. Our work seeks to explore the design of architectures for such AI agents based on core principles that can be traced back to the early pioneers of AI but are not fully utilized in modern AI methods. We do so in this paper in the context of the core problem of AI agents addressing ambiguity in the objects being referred to by the human participants. Humans address such ambiguity by heuristically leveraging compositional knowledge of domain context and the preferences of the other human participants. Drawing inspiration from this observation, we describe an architecture that embeds the principle of hierarchical compositionality and uses simple heuristics to achieve the desired disambiguation. Specifically, domain objects are represented in terms of primitive attributes drawn from human-validated semantic feature norms, and a hierarchical combination of attributes and concepts automatically identified from a limited observed history of interactions of an assistive agent with specific users. The assistive agent then achieves the desired disambiguation by reasoning with knowledge of this compositional hierarchy; axioms governing domain dynamics; and models of semantic compatibility, session salience, and user-specific thematic preference, requesting human clarification when necessary. Experiments show that our approach consistently outperforms state of the art data-driven baselines, supporting adaptation to specific user profiles.

Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.

Agentic artificial intelligence has shown great promise in automating algorithm design, but scaling similar techniques to computer microarchitecture discovery remains challenging due to vast search spaces, strict hardware budgets, and long simulation times. In this work, we present ArchAgent v2, a framework which scales automated microarchitecture search to multi-level data prefetching. While the original ArchAgent successfully discovered single-level cache replacement policies in competition settings, it does not scale to multi-level prefetching where the design space and degrees of freedom are larger. To overcome this, we introduce two new additions to ArchAgent: a cascaded evolutionary search that subdivides the design space by sequentially evolving and freezing prefetchers at individual cache levels, and a hardware-realizability feedback loop that embeds real-time size-estimation directly into the evolution process. Evaluated under identical rules of the 4th Data Prefetching Championship (DPC4), ArchAgent v2 automatically designs a three-level prefetcher that outperforms the winning hand-designed solution, further demonstrating automated agentic discovery as a useful tool for computer architects. Our discovered policy achieves a 3.8% geometric mean IPC speedup over the baseline overall and a 0.3% improvement over the prior champion, BertiGO. On low-bandwidth single-core configurations, our policy yields a 4.6% performance speedup compared to only 2.6% for BertiGO. However, multi-core evolution still remains a significant challenge due to simulation latency impeding evolution speed. Finally, our profiling of an ArchAgent evolution of over 12,000 candidate designs provides key insights into how automated evolutionary agents explore and synthesize complex microarchitectural logic.

A model alone does not determine how a programming agent acts. What the model sees, how actions enter the environment, how feedback returns, and how one run affects the next all depend on how the harness is organized. Minimal examples usually show only the basic interaction between a model and tools, while production systems spread these relationships across complex components and dependencies. This paper studies a compact harness design by following a single request through context formation, model decision, environmental action, observation return, and state continuation. Three boundaries---model, execution, and state---connect the model service, tool environment, and persistent state, while the request lifecycle determines the order in which these transitions occur. Together, they show the harness's core role: turning model generations into environmental actions, carrying runtime feedback into later decisions, and allowing state to continue across requests. On top of this runtime structure, a harness can also be gradually refined across runs through continued bootstrapping. The design is realized in the executable artifact https://github.com/lilinxi/Coderlet.

Quantum low-density parity-check (qLDPC) codes can encode multiple logical qubits using sparse parity checks, yet searching for useful finite-length instances remains a challenging design problem because code performance must be optimized while satisfying practical constraints. Motivated by recent advances in artificial-intelligence agents for scientific discovery, we develop a multi-agent framework for discovering practical qLDPC codes. The framework combines specialist proposal and review, persistent scientific memory, long-horizon evolution of executable programs, and deterministic construction and evaluation within a closed-loop search. These programs instantiate coset-orbit balanced-product codes, providing a search space that includes bicycle and lifted-product constructions as well as non-normal subgroup actions. To incorporate practical constraints, we restrict the search to binary CSS codes with block length $n\leq400$ and overall weight $w\leq10$. Within this regime, the framework discovers codes with leading or competitive rate--distance performance in every weight class considered, with representative instances including $[[288,16,18]]$ at $w=7$, $[[288,18,18]]$ at $w=9$, and $[[234,28,18]]$ at $w=10$. The search also uncovers structurally distinct, high-performing constructions, including a $[[336,12,\leq24]]$ candidate and a $[[368,18,16]]$ code, both of which are genuine balanced-product constructions with non-normal subgroup actions. When evaluated under code-capacity depolarizing noise using a common BP-OSD decoding protocol, the discovered codes also exhibit low logical failure rates. Together, these results provide hardware-relevant finite-length candidates for further experimental evaluation and show how structured agentic search can contribute to scientific discovery.