Daily Digest 2026-06-17

ArXiv ID: 2606.17209

Authors: Sidhaarth Murali, Jo\~ao Coelho, Jingjie Ning, Jo\~ao Magalh\~aes, Bruno Martins, Chenyan Xiong

Abstract:

Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., more parallel rollouts). Here we focus on breadth scaling, showing that standard parallel sampling yields diminishing returns, tracing this to query redundancy at the first turn. When models issue similar first queries across rollouts, the threads retrieve overlapping evidence, and subsequent turns are conditioned on this shared retrieval. We address this limitation with DivInit, a training-free intervention at the first turn. Rather than sampling k independent first queries, DivInit draws n candidates from a single call, picks k < n diverse seeds, and runs them as parallel trajectories. Across five open-weight models and eight benchmarks, DivInit consistently improves over standard parallel sampling, with average gains of five to seven points on multi-hop QA at matched compute. Code available at https://github.com/cxcscmu/diverse-query-initialization

ArXiv ID: 2606.17328

Authors: Xianxuan Long, Zhikai Chen, Shenglai Zeng, Shouren Wang, Kai Guo, Jiliang Tang

Abstract:

LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, even when several questions probe the same fact, it cannot show how that fact behaves as conditions change. We introduce MemTrace, a benchmark whose unit of measurement is the knowledge point: a single typed fact about the user, rather than an individual question. MemTrace probes each fact along three controlled dimensions: memory age, defined by how many sessions ago the fact appeared in the history; question type, covering current state, earlier state, and trajectory of change; and evidence condition, covering present, missing, and contradicted-by-false-premise settings. Evaluating 13 memory-system configurations across four paradigms, we find that similar pooled accuracy hides different failures: recovering a fact's current and earlier states does not imply tracking how it changed, and safe abstention does not imply correcting a false premise. The dominant bottleneck is evidence use, not retrieval: when systems fail, the evidence was retrievable 10 times more often than it was missing. These results suggest that improving long-term memory requires better use of reachable evidence, not simply more storage or retrieval.

ArXiv ID: 2606.17368

Authors: Shengli Zhang, Deen Ma, Zibin Lin, Taotao Wang

Abstract:

Large language models have accelerated the transition from passive conversational assistants to autonomous agents that can understand goals, plan actions, invoke tools, and execute multi-step tasks. Yet the capability of a single agent remains constrained by its local data, tool permissions, runtime environment, and governance boundary. This paper studies distributed general-purpose agent networks: open peer-to-peer networks in which heterogeneous agents deployed on personal devices, edge nodes, or autonomous computing environments can discover one another, establish trust, negotiate cooperation rules, and execute open-ended tasks. We argue that such networks cannot be obtained by simply combining existing peer-to-peer overlays with conventional multi-agent systems. Unlike traditional P2P networks, agent networks must propagate semantic declarations about intentions, capabilities, states, and cooperation constraints. We therefore propose a layered architecture centered on a protocol adaptation layer that connects upper-level task semantics with lower-level network operations. Based on this architecture, the paper identifies three core mechanism problems: semantic announcement propagation for collaborator discovery, verifiable identity and multi-topic reputation for cooperation governance, and semantic-gradient mechanism design for open task execution. For each problem, we present a technical route, including bodyless gossip with sequential logs, BAID-based identity binding with MG-EigenTrust reputation, and a Stackelberg-style mechanism-generation loop driven by semantic attribution feedback. We further report prototype overhead results for BAID-style tiered verification and mechanism-level simulations of MG-EigenTrust under cross-topic disguise-collusion attacks. The resulting framework provides a system-level foundation for open, trustworthy, and scalable agent collaboration.

ArXiv ID: 2606.17453

Authors: Lubin Bai, Mengyu Cao, Sixue Wang, Zhongwei Wan, Yue Pan, Jiale Hou, Xiang Li, Xiuyuan Zhang

Abstract:

Large language model agents are increasingly integrated into map services. Since map services are embedded in everyday-life scenarios rather than professional task settings, users often express their needs informally, resulting in underspecified queries with many unspoken needs, namely, implicit decision factors that are critical for user satisfaction. Although clarification is an effective way to mitigate this issue, it increases user burden in daily interaction, and a capable agent should first proactively recover such factors from available information sources. However, evaluating this ability is challenging. The first challenge is to determine which implicit decision factors are suitable for evaluation. A factor is evaluable only if it affects user acceptance and can be recovered from information available to the agent before it responds. Second, user satisfaction cannot be reliably represented by a single reference answer, requiring a benchmark that converts satisfaction-relevant factors into objective and quantifiable evaluation targets. To address these challenges, we propose a restore-identify-filter framework that reconstructs complete user needs from behavior-chain evidence, identifies implicit decision factors, and retains only those supported by pre-query evidence. Building on this methodology, we construct MapSatisfyBench from large-scale, real-world anonymized user data and annotate ground truth from five dimensions and enables full-chain evaluation of satisfaction-aware map agents. Experiments show that current agents generally perform well on explicit task completion, but remain limited in satisfying implicit decision factors and proactively acquiring the evidence needed for satisfaction-aware decisions. These findings establish MapSatisfyBench as a benchmark for shifting map-agent evaluation from task completion toward satisfaction-aware spatial decision making.

ArXiv ID: 2606.17454

Authors: Gaurav Gupta, Vatshank Chaturvedi, Jun Huan, Anoop Deoras

Abstract:

AI agent performance is not just a modeling problem, it is fundamentally a systems problem. The advanced capabilities of models are realized through agent harnesses. Therefore, a gap between model assumptions and harness behavior can easily prevent the model's full capabilities from translating into agent performance. We formalize this as the `intent-execution' gap: the mismatch between what the model intends and what the harness executes, and vice versa. We argue that minimizing this intent-execution gap is as important as other aspects of harness design such as tools and execution loops. To illustrate the impact of this harness-model alignment, we develop a simple and customizable harness called `Simple Strands Agent' (SSA). SSA aims to find the bulk of common patterns which generalize across different model families (such as Claude, Gemini, GPT, Grok, Qwen), as well as a small number of model-specific preferences. We make two contributions: (i) we $\textbf{reproduce or improve on the pass@1}$ performance reported by diverse model-provider families on popular agentic benchmarks (SWE-Pro, SWE-Verified and Terminal-Bench-2), and (ii) building on an $\textbf{analysis of 138k trajectories generated by SSA}$, we look beyond the $\texttt{pass@1}$ numbers which tend to be relatively even across frontier models. By representing agent trajectories in code state-spaces, we observe model-level differences in problem-solving behavior. Finer-grained metrics such as edit frequency, testing activity, and phase-transitions reveal how individual models allocate effort across different stages of autonomous problem solving.

ArXiv ID: 2606.17459

Authors: Yuyang Dai, Xueqing Peng, Lingfei Qian, Zhuohan Xie

Abstract:

Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in stylized settings. These evaluations overlook the defining challenge of real executive decision-making: integrating conflicting recommendations from specialized stakeholders under information asymmetry, organizational constraints, and temporal dependencies. We introduce \textsc{CEO-Bench}, a multi-agent benchmark that evaluates LLMs on CEO-level strategic resource reallocation -- the process of redirecting capital across business units in a multi-round, constraint-rich organizational environment. In \textsc{CEO-Bench}, LLM agents receive conflicting advice from four role-conditioned C-suite advisors (CFO, CTO, COO, CMO), each with private signals and distinct priorities, and must synthesize these into a concrete allocation plan evaluated along four dimensions: role integration, conditional boldness, history-sensitive judgment, and plan validity. Experiments across five frontier models on 13 scenarios reveal that all models achieve high structural validity but diverge sharply on strategic calibration -- the hardest capability layer. We identify systematic failure modes including single-advisor capture, conservative default under ambiguity, and historical amnesia, and uncover a structural integration-boldness tradeoff: models that engage more deeply with conflicting perspectives tend to produce less decisive action. These findings delineate the current capability boundary of LLMs as organizational decision-makers and inform the design of future AI-assisted executive systems.

ArXiv ID: 2606.17546

Authors: Congjie Zheng, Chuanyi Xue, Bin Liang, Jun Yang, Changshui Zhang

Abstract:

Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop. Existing evaluations often reduce this process to isolated task scores or a single sequential curve, obscuring whether an update produces reusable improvement, overfits recent tasks, increases cost, or harms older behavior. We introduce SEAGym, an evaluation environment for measuring agent harness updates across training, validation, test, replay, and cost records. SEAGym turns Harbor-compatible benchmarks into dynamic self-evolution task sources with train batches, frozen update-validation, held-out ID and OOD transfer views, replay diagnostics, and saved snapshot and metric records. Instantiating SEAGym on Terminal-Bench 2.0 and HLE, we compare ACE, TF-GRPO, and AHE under a shared epoch/batch protocol. The results show that these evaluation views provide complementary signals about the evolution process: frequent updates may fail to improve held-out performance, useful intermediate snapshots may collapse later, and source diversity and model backend can affect harness reliability.

ArXiv ID: 2606.17312

Authors: Baishali Chaudhury, Mengdie Flora Wang, Hyunji Hayley Park, Rahul Ghosh, Sungmin Hong, Jae Oh Woo

Abstract:

Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently -- a failure mode especially prevalent in multi-step deductive reasoning. Existing methods assess reliability primarily through output dispersion -- measuring how much sampled answers differ -- but this discards a complementary signal: whether the model can consistently rank competing reasoning candidates. We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings over sampled reasoning solutions. Given a query, we generate multiple candidate solutions and ask the model to judge pairwise preferences among its own outputs. We aggregate self-preferences into ranking distributions via Bradley-Terry modeling with PageRank, and decompose the signal into two entropy-based components: across-trial ranking instability and within-trial candidate ambiguity. Across five LLMs and eight benchmarks, structural signals provide information complementary to answer dispersion: on logical and mathematical reasoning tasks, the combination improves identification of unreliable instances, while on factual retrieval the structural signal collapses toward uniformity, diagnosing a regime boundary where reasoning-level consistency evaluation is uninformative. The two components relate differently to accuracy: within-trial ambiguity correlates positively with correctness -- consistent with settings where multiple plausible solution paths remain competitive -- while across-trial instability correlates negatively, signaling unreliable reasoning. Structural uncertainty is best understood not as a universal confidence estimator, but as a regime-sensitive evaluator of logical reasoning consistency.

ArXiv ID: 2606.17289

Authors: Phoebe Zeng, Thomas L. Griffiths, Brenden M. Lake

Abstract:

AI systems based on artificial neural networks are being developed with aspirations of pushing the boundary of human mathematical knowledge. A key question for these systems is how much they can reach beyond their training data. Mathematical discovery requires a strong form of out of distribution generalization; the ability to hypothesize genuinely new - and potentially logically more powerful - mathematical structures. It has been hypothesized that language abilities support such generalizations in human cognition. In this work, we use simple arithmetic as a case study for examining how modern AI models could expand their mathematical horizons, evaluating whether these models can independently discover the concept of "zero". We show that We show that (1) language models of a GPT-2 size are unable to perform this generalization at test time regardless of language pretraining, but (2) models can improve substantially after training on tens or hundreds of examples of zero. Additionally, we find that language pretraining reduces the number of required examples by approximately $50\%$, showing that language abilities can scaffold mathematical discovery in neural models.

ArXiv ID: 2606.17443

Authors: Xi Chu, Yupeng Hou

Abstract:

Large language models (LLMs) are becoming a major way for consumers to find products, but we do not yet understand how brands compete in this new channel. We study brand dynamics in LLM recommendations using skincare products -- a category where consumers cannot easily judge quality before buying and must rely on brand reputation -- across three commercial LLMs (GPT-4o-mini, Claude Sonnet, Gemini 3 Flash), with a robustness check on search goods. In three experiments, we find: (1) a Conditional Monopoly where well-known brands get recommended 100% of the time (IAI = 10.0) when all products have the same specifications, but this dominance disappears with less than a +0.1-star rating advantage for a competitor; (2) authority-style marketing language, including fabricated clinical-evidence claims, breaks this monopoly at a Bias Surplus Value equal to +0.17 rating points, with each model responding differently; and (3) a social dilemma in multi-brand GEO competition: when all brands adopt the same optimization strategy, individual payoff falls from +0.802 to +0.007 in our payoff proxy, and non-participating brands receive zero recommendations in our tests. Our results suggest that generative engine optimization (GEO) should be studied not only as a security risk, but also as an emerging marketing practice that shapes market competition.

ArXiv ID: 2606.17507

Authors: Xiwei Xu, Chen Wang, Jacky Jiang, Phil Yang, Qian Fu, Mohan Dhall, Wenjie Zhang, Liming Zhu

Abstract:

Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground model outputs in authorised curriculum artefacts and marking guidelines issued by education authorities. This paper presents a curriculum-grounded, configurable LLM-as-Judge pipeline for question-level marking, co-developed with an industrial partner, to support exam preparation for university admission. The pipeline identifies the relevant topics, subtopics, and cognitive demand of a question, and assembles verifiable and authorised context to support LLM judgement. Curriculum intent is operationalised through concrete syllabus artefacts, including prescribed verbs and outcomes, performance band descriptors, glossary definitions, and marking-guideline principles. A staged LLM workflow is employed to first generate question-specific rubrics, capturing structured expectations of performance, and then derive and evaluate marking criteria used to allocate marks to student responses. This design improves consistency, transparency, and alignment with official marking practices. Preliminary evaluation shows that the proposed LLM-as-Judge pipeline delivers marking outcomes comparable to human tutors, while yielding justifications that are more traceable to authorised curriculum artefacts and marking standards. The pipeline has also been integrated into an online study platform, where early deployment data provide initial insights into operational usage and manual overrides.

ArXiv ID: 2606.17220

Authors: Mingxu Tao, Jiawei Hu, Xian Zhou, Wenpeng Hu, Jiajun Cheng, Yunbo Cao, Zhunchen Luo, Guotong Geng

Abstract:

Legal case retrieval remains challenging due to the complexity of legal language and the need for precise lexical alignment between queries and relevant cases. Although dense retrieval models have achieved notable progress, empirical studies show that BM25 continues to serve as a strong baseline in this domain. It motivates us to propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training. The framework equips an LLM-based agent with an automatic evaluation environment, enabling it to iteratively create rewriting rules, plan validation experiments over rule combinations, and eliminate ineffective rules based on historical feedbacks. We evaluate our method on the Chinese legal case retrieval benchmark LeCaRD-v2. Experimental results demonstrate that the proposed framework outperforms non-evolutionary baselines, including human-designed rules and greedy rule selection, particularly when powered by a highcapacity core LLM. We also conduct detailed analyses to investigate the mechanisms underlying self-evolution. Our findings reveal that LLM's capabilities to leverage previous experimental results and its intrinsic knowledge of rule elimination play critical roles in refining the rule set via self-evolution.

ArXiv ID: 2606.17591

Authors: Yanwei Cui, Xing Zhang, Yulong Zhang, Li Shao, Xiaofeng Shi, Guanghui Wang, Peiyang He

Abstract:

Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes. However, in non-stationary environments these agents face a retention-forgetting dilemma: retaining stale insights causes negative transfer, while discarding them causes catastrophic forgetting when conditions recur. We identify four requirements for navigating this dilemma -- outcome-driven evaluation, persistent structured evidence, non-monotonic knowledge lifecycle, and compositional governance -- and show that existing methods invest heavily in experience extraction while underinvesting in insight governance. We propose a three-layer architecture -- rules, evidence, and skills -- connected by a feedback-driven curation loop that closes the governance gap. Rules capture distilled experience from world outcomes; evidence logs track each rule's reliability across episodes; skills govern which rules to apply, how to resolve conflicts, and when to abstain. On financial forecasting as a case study, where world feedback is naturally abundant, noisy, and non-stationary, we show that the same accumulated experience either degrades performance below the zero-shot baseline or dramatically improves accuracy and risk-adjusted returns, depending on whether the curation loop is present.

ArXiv ID: 2606.17405

Authors: Xinyu Qin, Anil K. Sood, Ruiheng Yu, Sara Corvigno, Elaine Stur, Lu Wang

Abstract:

Clinical decision support AI systems (CDSASs) must adapt to evolving patient conditions in real-time while adhering to strict safety constraints. We present an online adaptive framework that integrates Treatment Effect (TE) estimation to quantify clinical benefits, a patient Digital Twin (DT) to simulate treatment trajectories, and Reinforcement Learning (RL) for sequential decision-making. The AI system is initially trained on historical medical records and operates in a continuous learning loop. To ensure safety, a rule-based module monitors vital signs and blocks contraindicated treatments. Cases with strong internal model disagreement are flagged for clinician review, simulated in our experiments via a pre-trained outcome model. We validate our framework using both a synthetic clinical simulator and a real-world ovarian cancer dataset from The Cancer Genome Atlas (TCGA). In both simulated and clinical settings, our method demonstrated superior effectiveness and stability in recommending treatments compared to standard computational baselines. Furthermore, the AI system maintains low latency and requires expert consultation for only a minority of cases in our experimental validation, demonstrating its potential as a safe, clinician-supervised tool for personalized medicine that continuously improves through practical use.

ArXiv ID: 2606.17574

Authors: Siyi Li, Chunyu Sun, Jiahao Zhang, Yuchen Kang, Wuliang Wang, Yu Qiu, Rui Jiang, Haitao Cui, Jie Chen

Abstract:

Evaluating a Physical AI stack spans operators that differ by more than three orders of magnitude -- from a single foundation-model decoding step to thousands of physics ticks of whole-body control -- varying orthogonally in modality, reward semantics, and resource profile. No existing framework spans this range, so the stack is evaluated today by stitching together separate harnesses that share neither runtime nor scoring, preserving each segment's local validity but losing the shared identity needed to diagnose cross-layer regressions. We present DeepInsight, an evaluation infrastructure that serves this full spectrum on a single runtime. Rather than homogenize the regimes, it preserves their heterogeneity behind three narrow abstractions -- task, resource, and result -- each realized as one invariant shared by every subsystem: one episode driver, one resource-handle protocol implemented by every expensive backend (LLM inference and sandboxed runtimes alike), and one trace identity scheme under which every event is written. Deployed in production across all three layers of an embodied humanoid stack, this single set of invariants onboards new benchmarks largely by configuration. Where mature peer orchestrators exist -- at the foundation-model end -- it reproduces published references and peer-framework readings within their own spread, runs the same suites faster on a single node, and scales near-linearly across nodes. Its distinctive return is diagnostic: because every layer writes into one shared trace, a regression that begins in one layer and surfaces in another stays localizable on that trace -- a cross-layer payoff no federation of per-segment harnesses can reproduce.

ArXiv ID: 2606.17577

Authors: Osamu Ito, Akihiko Katagiri, Yoshikazu Nakagawa, Shin Saeki, Jun Shiraishi, Masato Sasaki

Abstract:

AI-driven engineering workflows face particular challenges in crash safety design: unlike aerodynamics, crash events involve highly nonlinear contact dynamics, material nonlinearity, and discrete state transitions that are difficult to capture with data-driven surrogate models. To the best of our knowledge, we present the first foundation model--orchestrated workflow for crash safety design that enables surrogate-assisted exploration for pedestrian protection, reducing evaluation time from hours per CAE simulation to seconds. The workflow integrates four components: (1) a surrogate trained on CAE crash simulations to predict pedestrian leg injury metrics from design parameters, achieving an average $R^2=0.87$ and providing distribution-free conformal prediction intervals; (2) multiobjective evolutionary search (NSGA-II) to discover diverse feasible parameter sets under user-specified constraints; (3) a morphing-based geometry generator that maps parameters to topology-preserving 3D shapes; and (4) a natural-language interface in which an LLM orchestrates the workflow and a vision--language model supports semantic comparison of generated designs. In an automotive front-bumper case study, the workflow produces 35 distinct safety-compliant alternatives from a single exploration, a process that would require weeks with conventional CAE iteration. These results suggest that foundation models can serve as integration layers between ML surrogates and physics-based simulation, helping bring AI capabilities to safety-critical engineering domains.

ArXiv ID: 2606.17339

Authors: Sejal Bhalla, Larry Kieu, Aina Merchant, Eyal de Lara, Alex Mariakakis

Abstract:

Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems. Current clinical speech AI methods have largely progressed through isolated condition-specific studies, making results difficult to compare and generalization difficult to assess. We introduce SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions. To enable evaluation across shared clinical mechanisms, SpeechDx structures tasks by the stage of speech production they disrupt: conceptualization, formulation, and articulation. The benchmark tests generalization by including tasks with limited labeled data and evaluating the same health condition across multiple datasets, distinguishing clinically meaningful patterns from dataset artefacts. We systematically evaluate 12 state-of-the-art audio encoders across all tasks and under zero-shot cross-condition transfer. Results show that large-scale speech models represent the strongest overall baselines, domain-specific models improve performance only on closely matched tasks, and no current representation generalizes reliably across the clinical speech landscape. SpeechDx establishes a shared evaluation framework for tracking progress toward general-purpose clinical speech representations

ArXiv ID: 2606.18065

Authors: Dexing Liu

Abstract:

As LLM-driven multi-agent systems (MAS) transition from lab to production, system behavior exhibits nonlinear degradation. We introduce the Intelligence Entropy Principle: probability-driven systems spontaneously drift toward disorder, formalized as S(t) = S0 * exp(alpha*t/Cm), where Cm is a model capability coefficient we propose. Lyapunov analysis yields the stabilization condition lambda > alpha/Cm. We construct the ADE (Agent Delivery Engineering) four-layer framework (L1 Physical Laws through L4 User Adaptation) with 23 core components. Validation spans 100K-scale experiments and 33.6 days of production monitoring. We propose a Five-Layer Disorder Taxonomy unifying failures under structural collapse, and present Elastic Organization as an original MAS morphology. Results: channel fracture reduced from 69-98% to near 0%; system death probability below 0.02%.

ArXiv ID: 2606.17962

Authors: Marco Aruta, Vadim Malvone, Aniello Murano, Domenico Parente, Luca Rizzuti

Abstract:

Reasoning about what agents can achieve through strategic interaction is a core challenge in Multi-Agent Systems (MAS). Logics for strategic ability, such as ATL, provide rigorous methods, but their adoption is often hindered by the computational cost of strategy synthesis. We introduce a neuro-symbolic framework that integrates large language models (LLMs) into the model-checking pipeline for MAS. The LLM acts as a strategy-generation oracle, proposing candidate strategies that are then formally validated by a standard MAS model checker. This generate-and-certify architecture uses LLM guidance to navigate large combinatorial strategy spaces while preserving formal soundness: generated strategies are accepted only when certified by the verifier. We instantiate the framework for bounded strategic reasoning in NatATL and introduce the first NatATL strategy-synthesis dataset, consisting of 4211 instances. Experiments with an open-weight Qwen3-32B model show that our certified pipeline achieves 92\% accuracy on strategy-synthesis outcomes.

ArXiv ID: 2606.17915

Authors: Aueaphum Aueawatthanaphisut, Badri Raj Lamichhane

Abstract:

Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data science agents and AutoML systems mainly focus on isolated workflow stages, leaving limited support for lifecycle-level orchestration, artifact governance, human oversight, and drift-aware adaptation. This paper proposes a trustworthy self-composable BDaaS frame work based on LLM-orchestrated multi-agent collaboration. The proposed architecture decomposes the BDaaS lifecycle into specialized agents for data ingestion, data cleaning, feature engineering, AutoML training, model evaluation, MLOps de ployment, monitoring, and drift detection. A central LLM or chestration layer coordinates agent execution, validates interme diate outputs, manages workflow context, and enables dynamic workflow composition. The framework also incorporates shared artifact governance, reproducibility support, human-in-the-loop checkpoints, and drift-aware feedback loops. A prototype-based evaluation is conducted using controlled tabular benchmark datasets with missing values, categorical variables, outliers, class imbalance, and simulated covariate drift. Compared with manual ML, AutoML-only, and single-agent LLM baselines, the pro posed multi-agent BDaaS pipeline achieves competitive predictive performance while improving lifecycle-level reliability, including workflow completion, artifact traceability, deployment readiness, reproducibility, and drift recovery. The results suggest that LLM-orchestrated multi-agent systems can extend conventional AutoML toward trustworthy, adaptive, and production-oriented BDaaS lifecycle automation.