subject

cs.MA

cs.MA: explore 66 source-linked works published from 2023 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-14. Counts describe this index, not the complete source archives.

arXiv2026

MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability

Large Language Model (LLM) agents deployed in complex real-world scenarios increasingly operate as spatially distributed entities. However, this physical dispersion constrains agents to limited local perception and finite temporal horizons. We characterize this bottleneck as spatiotemporal partial observability, where spatial and temporal limitations are fundamentally coupled: resolving spatial conflicts requires temporal reasoning about neighbors' future actions, while temporal planning requires spatial context beyond local perception. To bridge this gap, we introduce MACRO-LLM, LLM-empowered multi-agent collaborative reasoning under spatiotemporal partial observability. The architecture interleaves spatial and temporal reasoning within each decision cycle via three interdependent modules: (1) the CoProposer mitigates temporal uncertainty by verifying candidate actions via predictive rollouts; (2) the Negotiator overcomes spatial myopia by resolving conflicts through mean-field statistical aggregation, grounded in the CoProposer's rollout rewards; and (3) the Introspector closes the reasoning loop by analyzing environmental drift and attributing performance changes to refine strategies. Extensive evaluations on two complex long-horizon tasks, cooperative platoon planning and pandemic control, demonstrate that our framework enables robust coordination under spatiotemporal partial observability.

cs.MA↗

arXiv2026

MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems

Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness.

cs.MA↗

arXiv2026

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most environments are scored only by game outcomes such as win rates and largely remain to text-only interaction, making it difficult to tell whether an agent's language is actually grounded in what it perceived and did, or to identify the failure modes underlying its behavior. To address this gap, we introduce QUACK, an open-source environment and evaluation framework for auditing the grounding of agent language in multimodal social reasoning. QUACK evaluates agents at three levels: game outcomes, behavioral trajectories, and utterance-level consistency. Its core Statement Verification Pipeline reconstructs each agent's ground-truth trajectory from engine logs and checks every discussion claim against it, automatically flagging spatial hallucination, unsupported accusation, deception collapse, and language-action inconsistency. Evaluating three frontier VLMs in both homogeneous and cross-model adversarial settings, we find that even the strongest agent hallucinates 15.1% of its verifiable spatial claims and 11.5% of accusations are strictly unsupported. We release the full engine, evaluation framework, toolkit, and logs in https://github.com/AAAAA-Academia-Attractions/QUACK.

cs.CL↗

arXiv2026

Can Agentic Trading Systems Pay for Their Own Intelligence?

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter only by amplifying or degrading decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://anonymous.4open.science/r/TradeLens.

cs.AI↗

arXiv2026

The rise and evolution of a referential code in populations of bee-like agents

Communication typically relies on a shared code, and any change to it must be coordinated between senders and receivers to avoid a breakdown of communication. The honeybee waggle dance illustrates this problem: species with horizontal combs point directly at a food source, while species with vertical combs cannot point directly and instead reference the dance to gravity, decoded against the position of the sun. We model the rise of the first of these codes and its evolutionary transition to the second in populations of bee-like agents, with selection acting at the level of colonies. In a horizontal-comb model, we find that direct pointing evolves readily when food is moderately hard to find by random search alone, whether because sites are few and large or many and small, and fails when food is too sparse to spark dances or so abundant that it is found without signaling. Adding an exogenous benefit for vertical combs, we then find that the transition to the gravity-referenced code is driven mainly by the mutation rate and the magnitude of this benefit, with the coupling between sender and receiver mutations playing a further role at low mutation rates. Given a favorable confluence of these factors, the transition proceeds reliably and without a breakdown of communication.

q-bio.PE↗

arXiv2026

AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance

AI for Industrial Asset Lifecycle Management aims to automate complex operational workflows, such as condition monitoring and maintenance scheduling, to minimize system downtime. While traditional AI/ML approaches solve narrow tasks in isolation, Large Language Model (LLM) agents offer a next-generation opportunity for end-to-end automation. In this paper, we introduce AssetOpsBench, a unified framework for orchestrating and evaluating domain-specific agents for Industry 4.0. AssetOpsBench provides a multimodal ecosystem comprising a catalog of four domain-specific agents, a curated dataset of 140+ human-authored natural-language queries grounded in real industrial scenarios, and a simulated, CouchDB-backed IoT environment. We introduce an automated evaluation framework that uses three key metrics to analyze architectural trade-offs between the Tool-As-Agent and Plan-Executor paradigms, along with a systematic procedure for the automated discovery of emerging failure modes. The practical relevance of AssetOpsBench is demonstrated by its broad community adoption, with 250+ users and over 500 agents submitted to our public benchmarking platform, supporting reproducible and scalable research for real-world industrial operations. The code is accesible at https://github.com/IBM/AssetOpsBench .

cs.AI↗

arXiv2026

Language-Guided Tuning: Configuration Optimization for Automated ML Research

Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions independently and lack interpretability, while recent automated methods struggle with dynamic adaptability and semantic reasoning about optimization decisions. We introduce Language-Guided Tuning (LGT), a framework that employs multi-agent Large Language Models to automatically optimize configurations through natural language reasoning. We apply textual feedback signals that complement numerical optimization by providing semantic understanding of training dynamics and configuration interdependencies. LGT coordinates three specialized agents: an Advisor that proposes configuration changes, an Evaluator that assesses progress, and an Optimizer that refines the decision-making process, creating a self-improving feedback loop. Through comprehensive evaluation on seven diverse datasets, LGT demonstrates substantial improvements over traditional optimization methods while maintaining high interpretability.

cs.AI↗

arXiv2026

Characterising Global Platforms: Centralised, Decentralised, Federated, and Grassroots

Global digital platforms are distributed systems designed to serve entire populations, with some already serving billions of people. Here we propose atomic transactions-based multiagent transition systems and protocols as a formal framework to study them; introduce essential agents---minimal sets of agents the removal of which makes communication impossible; and show that the cardinality of essential agents partitions all global platforms into four classes: 1. Centralised (Facebook) -- one (the server) 2. Decentralised (Bitcoin) -- finite >1 (bootstrap nodes) 3. Federated (Mastodon) -- infinite but not universal (all servers) 4. Grassroots (Scuttlebutt) -- universal (all agents but one) Our illustrative formal example is a global social network, for which we provide centralised, decentralised, federated, and grassroots specifications via multiagent atomic transactions, and prove they all satisfy the same basic correctness properties, yet have different sets of essential agents as expected. We discuss informally additional global platforms---currencies, "sharing economy" apps, AI, and more. This work provides the first mathematical framework for classifying any global platform---existing or imagined---by providing a multiagent atomic-transactions specification of it and determining the cardinality of the minimal set of essential agents in the ensuing multiagent protocol. It thus provides a unifying mathematical approach for the study of global digital platforms, perhaps the most important class of distributed systems today.

cs.DC↗

arXiv2026

Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting

This paper addresses multi-objective conflicts and catastrophic forgetting in uncrewed aerial vehicle (UAV) networks across dynamic spatiotemporal environments. Conventional multi-agent reinforcement learning (MARL) algorithms suffer from severe policy degradation during sequential task transitions. We propose a spatiotemporal continual federated learning (SCFL) framework driven by the group-decoupled multi-agent proximal policy optimization (G-MAPPO) algorithm. SCFL incorporates a three-stage geometric alignment mechanism: it resolves local gradient conflicts via group-decoupled policy optimization (GDPO), mitigates spatial Non-Independent and Identically Distributed (non-IID) client drift through adaptive cosine aggregation, and suppresses inter-task interference via global temporal orthogonal projection without raw experience replay. Evaluations show that SCFL achieves superior robustness over federated baselines, maintaining spatial service reliability above 0.95 and a load balancing index of approximately 0.95 during non-stationary transitions. A longitudinal self-degradation analysis further shows that SCFL preserves historical knowledge with near-zero performance variation in spatial reliability and QoS under moderate loads from 40 to 120 users, while revealing its operating boundary under extreme congestion with 140 users due to hard projection constraints. The framework provides a scalable, communication-efficient approach for autonomous aerial network orchestration.

cs.NI↗

arXiv2026

Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI (Full Version)

Grassroots Logic Programs (GLP) is a concurrent logic programming language in which logic variables are partitioned into paired readers and writers. An assignment is produced at most once via a writer and consumed at most once via its paired reader, and may contain additional readers and/or writers. This enables the concise expression of rich multidirectional communication modalities. The language was introduced together with concurrent (cGLP) and multiagent (maGLP) operational semantics. Here, we derive from these (1) dGLP, a deterministic counterpart of cGLP, and (2) madGLP, a counterpart of maGLP in which deterministic agents communicate solely by asynchronous message passing, and prove them correct against their abstract counterparts. maGLP shared variable pairs spanning agents can be implemented by two local variable pairs joined by a \emph{global link}, with correctness following from disjoint substitution commutativity (a consequence of GLP's single-occurrence invariant). We further prove that madGLP is grassroots. Both dGLP and madGLP serve as formal specifications for an AI-driven implementation discipline (math $\to$ informal spec $\to$ Dart) employed and described here: from dGLP, AI (Claude) developed a workstation-based GLP implementation in Dart, and from madGLP it is developing a smartphone-based multiagent one.

cs.PL↗

arXiv2026

ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.

cs.MA↗

arXiv2026

Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents

Time Series Event Detection (TSED) aims to localize semantically meaningful events in time series data, with critical applications in high-stakes domains. Unlike statistical anomalies, events are often defined by natural-language descriptions with internal temporal-logic structures across multiple physical channels. However, in real-world settings, dense event annotations are expensive to obtain, making purely supervised learning difficult. We introduce Language-guided TSED, a setting where a model is given textual event descriptions and must ground them to intervals in multivariate signals with little or no labeled data. To address this problem, we propose Event Logic Tree (ELT), a knowledge representation framework that converts linguistic descriptions into structured temporal logic over signal primitives. Building on ELT, we present SELA, a neuro-symbolic VLM agent framework that iteratively grounds primitives from signal visualizations and composes them under ELT constraints, producing both event intervals and faithful tree-structured explanations. We further release a real-world benchmark across energy and climate domains with expert knowledge and annotations. Experiments show that SELA improves over supervised fine-tuning and existing zero/few-shot time series reasoning baselines.

cs.LG↗

arXiv2026

Robust Multi-Agent LLMs under Byzantine Faults

Large language model (LLM) agents increasingly collaborate over peer-to-peer networks to improve their reliability. However, these same interactions can also introduce vulnerability to unreliable or Byzantine agents that can propagate incorrect information and degrade overall system performance. To address this, we propose Self-Anchored Consensus (SAC), a fully decentralized filter-and-refine protocol in which agents iteratively exchange responses, locally evaluate and filter unreliable messages, and refine their own outputs. We present $(F{+}1)$-robustness conditions on the communication graph that ensure honest agents preserve and propagate reliable information despite Byzantine influence. Experiments across diverse open- and closed-weight LLMs on mathematical and commonsense reasoning benchmarks show that SAC effectively suppresses Byzantine influence and consistently improves performance across diverse communication topologies, whereas prior methods degrade significantly under Byzantine attacks.

cs.MA↗

arXiv2026

ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research

Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed feedback for evaluating outline modifications. We propose ScaffoldAgent, a utility-guided dynamic outline optimization framework for OEDR. ScaffoldAgent models outline evolution as a structured decision process with three operations: Expansion, Contraction, and Revision, enabling controlled updates to the report scaffold. It further introduces a utility-guided feedback mechanism that estimates the downstream value of each outline operation from retrieval gain, structural coherence, and trial-generation quality. The resulting utility signal guides node selection, operation scheduling, and termination during inference. Experiments on DeepResearch Bench and DeepResearch Gym show that ScaffoldAgent consistently improves long-form report generation and factual grounding over existing deep research agents.

cs.AI↗

arXiv2026

Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World

Machine intelligence's push into the physical world is stuck on a gap: deployment demands auditable judgments from day one, fault samples are scarce or absent, and the norms defining "what counts as a fault" live in design documents, not in operational data. We argue this gap is structural, and locate where it can be legitimately closed. We divide the worlds machine intelligence faces into four (phenomenal, basic physical, artificial physical, artificial symbolic) along one axis of constraint strength, and give the Promulgation Criterion: extracting a prior framework from a world is legitimate if and only if the world is intentionally constituted (C1) and has left a readable generative archive (C2). On the criterion's two gradient axes, exactly one world is high on both: the artificial physical world (buildings, factories, infrastructure), whose norms precede their instances; the legitimate path is to extract the framework from the archive, not to induce it from data. We then show what shape such a framework must take: four construction goals force four incompatible carriers, hence at least four layers (syntax, concepts, knowledge, instances); on a closed concept layer fault localization is decidable in polynomial time, and every judgment is interrogable, traceable to a promulgated clause. The same criterion fixes the runtime division of labor with LLMs: promulgatable duties go to rule engines, on-site judgments beyond promulgation go to LLMs, and every generation sandwiched by promulgated clauses is auditable. The theory is falsifiable: four bets (P1-P4) with explicit falsification conditions -- among them that the next large-scale AI breakthrough occurs in the artificial physical world. Evidence: formal proofs (Appendix A); two cases (Appendix B: a cooling plant; the Curiosity rover Sol 1536 anomaly); eight reverse-read lineages, from BACnet to RDF/OWL (Appendix C).

cs.AI↗

arXiv2026

MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model

Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with information overload, alert fatigue, and time-constrained decision-making. Although large language models (LLMs) have demonstrated promising capabilities for question answering (QA), their effectiveness in cybersecurity remains limited by insufficient domain knowledge, a tendency to hallucinate, and difficulties in capturing both semantic and structural relationships. This work proposes MITRE-SAGE, a multi-agent retrieval-augmented generation framework that integrates semantic and structural cybersecurity knowledge to improve the reliability and interpretability of LLM-based QA systems. By decomposing complex tasks into query interpretation, evidence retrieval, and answer synthesis, MITRE-SAGE effectively supports cybersecurity tasks such as vulnerability assessment, threat profiling, and relationship extraction. Furthermore, we propose MITRE-QA, a comprehensive benchmark comprising 3,000 question-answer pairs for evaluating LLMs across diverse cybersecurity knowledge tasks, and use it to systematically evaluate MITRE-SAGE against representative baseline methods. Extensive experiments demonstrate that MITRE-SAGE consistently outperforms standalone LLMs and conventional RAG approaches. Notably, a lightweight configuration comprising Qwen2.5-7B sub-agents and a Qwen2.5-14B orchestrator achieves superior performance on five of the eight benchmark tasks, indicating the effectiveness of the proposed multi-agent framework. The results highlight the potential of MITRE-SAGE as a scalable and interpretable approach for reliable cybersecurity QA, while MITRE-QA provides a standardized benchmark for future research.

cs.IR↗

arXiv2026

Candidate supply and answer selection shape the value of LLM judging in multi-agent systems

Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is difficult because generation, communication and final answer-selection rules usually change simultaneously. We conceptualize multi-agent reasoning as an evolutionary pipeline of candidate generation, peer communication and terminal selection, wherein consensus without quality control can exhibit patterns of memetic drift. We study two questions: (1) when an LLM judge provides effective selection pressure by supplying a signal of answer correctness for candidates generated in a multi-agent system, and (2) when using that signal improves the reported answer. To map judge reliability, we analysed 15,336 questions from MMLU-Pro, GPQA, MedXpertQA and MuSR, with Humanity's Last Exam analysed separately. To test these rules, we replayed 81,390 fixed candidate pools drawn from 16,278 questions across five benchmarks. We report three findings. (1) A correct answer is often already present among the generated candidates, but the system can still converge on and report a wrong answer. (2) Judge reliability is not a fixed trait of the model, but varies with the task, the generator and how rare the correct answer is. (3) Combining answer frequency with the judge's evaluation changed only the final answer-selection rule and raised accuracy from 63.82% to 70.82-70.95%, primarily by rescuing correct answers that were outnumbered by popular errors. In the systems studied here, the value of generating more candidates depends on whether those extra samples make correct answers present, frequent or recognisable. By isolating generation, recognition and selection, these findings establish a diagnostic basis for designing multi-agent architectures that protect generated correct answers from being lost.

cs.AI↗

arXiv2026

ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRouter, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets. ProgRouter introduces a multi-view task progress scorer that combines coarse workflow outcome regimes with fine-grained signals on subtask completion, progress trends, and workflow state quality. Then, a dual-path task progress predictor and an adaptive meta-gating mechanism estimate the progress gain for each candidate routed LLM. ProgRouter makes online step-wise routing decisions that balance progress gain, task time budgets, and long-term operating cost efficiency. Experiments on HumanEval Plus, MBPP, MATH-500, and ASQA, spanning agentic code generation, mathematical reasoning, and retrieval-augmented long-form question answering, demonstrate that ProgRouter reduces the operating cost relative to key baselines while maintaining strong task-solving performance.

cs.AI↗

Compare source metadata on this page

Work	Published	Source identifier	Source
MACRO-LLM: LLM-Empowered Multi-Agent Collaborative Reasoning under Spatiotemporal Partial Observability	2026-08-31	2601.09295	arxiv
MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems	2026-08-31	2602.13671	arxiv
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents	2026-08-31	2605.27068	arxiv
Can Agentic Trading Systems Pay for Their Own Intelligence?	2026-08-31	2607.10286	arxiv
The rise and evolution of a referential code in populations of bee-like agents	2026-08-31	2608.25779	arxiv
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance	2026-08-30	2506.03828	arxiv
Language-Guided Tuning: Configuration Optimization for Automated ML Research	2026-08-30	2508.15757	arxiv
Characterising Global Platforms: Centralised, Decentralised, Federated, and Grassroots	2026-08-30	2511.03286	arxiv
Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting	2026-08-30	2601.21861	arxiv
Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI (Full Version)	2026-08-30	2602.06934	arxiv
ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies	2026-08-30	2602.14681	arxiv
Grammar of the Wave: Towards Explainable Multivariate Time Series Event Detection via Neuro-Symbolic VLM Agents	2026-08-30	2603.11479	arxiv
Robust Multi-Agent LLMs under Byzantine Faults	2026-08-30	2605.09076	arxiv
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research	2026-08-30	2606.20122	arxiv
Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World	2026-08-30	2608.15147	arxiv
MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model	2026-08-30	2608.16921	arxiv
Candidate supply and answer selection shape the value of LLM judging in multi-agent systems	2026-08-30	2608.25937	arxiv
ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs	2026-08-30	2608.25992	arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.