Searcharxiv⌕ Search

subject

cs.MA

cs.MA: explore 220 source-linked works published from 2023 to 2026, with original documents and citations.

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

Search within this collection

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 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay

Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution cannot distinguish a jointly necessary repair from alternative singleton repairs. We formulate Minimal Repair Family Recovery (MRFR): recovering all inclusion-minimal event sets whose counterfactual replay restores task success within a declared size bound. We propose Graph-Constrained Joint Replay (GCJR), which slices failure-relevant events from an execution dependency graph, constructs graph-feasible singleton and pair candidates, and verifies them by replay with paired clean counterparts. For fixed replay outcomes, GCJR is exact within its declared graph domain. On 90 in-scope cases from a 120-DAG controlled benchmark, GCJR achieves 1.000 Family Exact Match while reducing mean replay calls from 56.3 to 25.3 (55.1%) relative to exhaustive search. On a 24-case, four-agent LLM pilot, it again achieves 1.000 Family Exact Match and reduces mean model calls from 21.0 to 10.0 (52.4%); single-event replay misses jointly necessary repairs.

cs.AI↗
arXiv2026

Adaptive stabilization of a leaderless bearing-constrained formation with disturbances

In this paper, we consider the problem of regulating and maintaining a target formation characterized by a set of bidirectional bearing constraints under disturbances. The agents in the formation are modeled by single integrators with bounded continuous disturbances of which the upper bound is unavailable for the control design. Due to the time-varying disturbances, the target formation is time-varying. We propose adaptive sliding mode control laws to uniformly globally asymptotically stabilizes the moving target formation and reject the matched disturbances. In addition, to alleviate chattering phenomena from sliding mode control, smooth adaptive control laws are then designed to guarantee uniform global boundedness of the desired formation. Finally, simulation results are given to support the analysis.

cs.MA↗
arXiv2026

CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems

Agentic systems require secure and efficient delegation of privileges across multiple collaborating agents. Existing approaches fall into two categories. Some propagate user identities directly to agents, obscuring accountability and creating persistent over-privilege risks that are amplified by the non-deterministic behaviour of AI agents. Others rely on continuous synchronization with a central Identity and Access Management (IAM) provider, introducing additional latency and communication overhead. We present CAPMAS, a novel architecture for secure end-to-end query execution in multi-agent systems. CAPMAS newly combines a contrastive learning-based semantic scoping pipeline that maps natural-language queries to bounded privilege sets before execution with expressive Macaroon-based tokens that enable offline, tamper-evident delegation with monotonic privilege reduction across agents. By decoupling authentication and delegation enforcement from agent reasoning, CAPMAS enables practical agentic execution while enforcing strict least-privilege guarantees. By eliminating synchronous delegation exchanges with the IAM, CAPMAS yields 30 times faster delegation operations, 2 times less delegation-oriented latency and up to 3 times lower bandwidth usage than the OAuth 2.0 Token Exchange (RFC 8693). Its semantic scoping pipeline achieves over 90% perfect privilege-bundle retrieval within 17 milliseconds on enterprise-scale API schemas containing over 3,100 endpoints, while reducing unnecessary privileges by 99.5% when compared to systems that propagate all the user's privileges to agents.

cs.MA↗
arXiv2026

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) has achieved significant progress in large-scale traffic control, autonomous vehicles, and robotics. Drawing inspiration from biological systems where roles naturally emerge to enable coordination, role-based MARL methods have been proposed to enhance cooperation learning for complex tasks. However, existing methods exclusively derive roles from an agent's past experience during training, neglecting their influence on its future trajectories. This paper introduces a key insight: an agent's role should shape its future behavior to enable effective coordination. Hence, we propose Role Discovery and Diversity through Dynamics Models (R3DM), a novel role-based MARL framework that learns emergent roles by maximizing the mutual information between agents' roles, observed trajectories, and expected future behaviors. R3DM optimizes the proposed objective through contrastive learning on past trajectories to first derive intermediate roles that shape intrinsic rewards to promote diversity in future behaviors across different roles through a learned dynamics model. Benchmarking on SMAC and SMACv2 environments demonstrates that R3DM outperforms state-of-the-art MARL approaches, improving multi-agent coordination to increase win rates by up to 20%. The code is available at https://github.com/UTAustin-SwarmLab/R3DM.

cs.MA↗
arXiv2026

Modal Logic Neural Networks

Neural Networks are indispensable to natural sciences and society. Their impact extends from applications in public health to workforce productivity. Here, we introduce Modal Logic Neural Networks (MLNNs) -- an end-to-end differentiable logical neural network realisation of modal logic which evaluates a learnable truth function across possible-world semantics. This neural architecture handles para-consistency and inconsistency via a learnable world accessibility relation and valuation function. Because the modality is fixed by which frame axioms the relation satisfies rather than by the operator, one differentiable engine covers the epistemic, doxastic, deontic and temporal readings, with applications from verification of reactive and distributed systems to legal discourse and microeconomic utility models. In this paper, we introduce a model of differentiable Kripke semantics, and establish their soundness, convergence, and structural guarantees. We show four applications, in which the learned relation reads as a trust matrix, an operating-regime embedding with safety bounds, a temporal precedence order, and a recovered constraint graph.

cs.LG↗
arXiv2026

Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning

In this paper, we propose the first VL\underline{\textbf{M}} \underline{\textbf{a}}gentic \underline{\textbf{r}}easoning framework for few-\underline{\textbf{s}}hot multimodal \underline{\textbf{T}}ime \underline{\textbf{S}}eries \underline{\textbf{C}}lassification (\textsc{MarsTSC}), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmark datasets demonstrate that \method{} delivers substantial and consistent performance gains across 5 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. Code is available at https://github.com/HuangJW0821/MarsTSC.

cs.AI↗
arXiv2026

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical context over long horizons untested. We introduce LongDS, a benchmark for long-horizon, multi-turn data analysis where agents must maintain, update, restore, and compose evolving analytical states. LongDS comprises 68 tasks constructed from real-world Kaggle notebooks, spanning 2,225 turns across six domains including Geoscience, Business, and Education. Tasks are designed around state-evolution patterns (e.g., counterfactual perturbation, rollback, multi-state composition), with an average dependency span of 11.3 turns. Evaluating five state-of-the-art models, we find that the best model reaches only 48.45% average accuracy, performance drops nearly 47 points from early to late turns, and long-horizon errors account for 52%--69% of failures. Further analysis shows that additional agent steps do not necessarily improve performance, suggesting that the key bottleneck is maintaining a correct analytical state rather than increasing interaction budget. We release LongDS to support research on reliable long-horizon agentic data analysis. Code and data are released at https://github.com/zjunlp/DataMind.

cs.LG↗
arXiv2026

Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions

Agents can turn shared infrastructure into a channel for coordinated intrusion. The Hugging Face incident and a separate public-wiki investigation show why a security assessment may need evidence from several executions and the artifacts they leave behind. We argue that the operational unit of defence should be a revisable coordination episode linking observed transfers, task authority, and response history. The central research problem is prospective episode discovery: finding which actions belong together before an evaluator supplies their membership. We define unsanctioned coordination relative to collaboration and delegated-authority policy, connect storage-mediated coordination to stigmergy, and specify the evidence needed to distinguish influence from common causes. First-contact signals are one possible input to discovery; the design also follows inherited state and later use. A proposed evaluation compares isolated actions, rolling windows, known groups, and prospectively discovered episodes at matched review cost and false-alert workload. It measures harmful outcomes across all assigned population runs and tests recurrence after channel closure and state quarantine. A checksum-verified reconstruction of the public wiki export separates the decline in retained writes from later administrative cleanup. The contribution is an incident-grounded position, descriptive analysis, and evaluation design. It makes the recommendation to monitor across executions testable without claiming a new detector or a measured containment benefit.

cs.CR↗
arXiv2026

Bundle Length Tradeoffs in Decentralized Multi-Robot Task Allocation Under Degraded Communications

Bundle length B is commonly fixed when configuring multi-task multi-robot task allocation (MRTA) algorithms. MinSum and MinMax are known to favor different task distributions, but the role of B in this objective tradeoff has not been systematically characterized. Additionally, degraded-communication evaluations also often retain settings selected under ideal communication, leaving whether nominal bundle-length tuning transfers under message loss unresolved. We examine both questions for ACBBA, PI, and HIPC across six bundle lengths in 300 paired ten-target Collaborative Visit scenarios under ideal communication and 25% Bernoulli packet loss. Under ideal communication, increasing B from 1 to 12 reduces MinSum cost by 19.0%, 23.0%, and 31.8% for ACBBA, PI, and HIPC, respectively, while increasing MinMax cost by 45.6%, 94.3%, and 67.6%. Under packet loss, the lowest-mean MinSum setting shifts from B = 12 to B = 2 for ACBBA and PI. Repeated paired cross-fitting shows that retaining the ideal-network setting incurs held-out MinSum penalties of 14.4% and 7.2%, respectively, and increases MinMax cost by 30.0% and 41.8% relative to the loss-conditioned MinSum setting. HIPC retains a deep MinSum operating region, while the MinMax setting remains stable for all three allocators. Experiments at two additional target loads reproduce the ACBBA and PI MinSum shifts.

cs.RO↗
arXiv2026

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction

Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs remains expensive because AW optimization requires evaluating a large number of candidate AWs via execution, resulting in high computational cost and latency. Recently, AW performance prediction has become a hot research topic to avoid costly execution-based evaluation, but existing methods primarily use Graph Neural Networks (GNNs) to model workflow structures and insufficiently capture the semantic relationships among agents. To address this limitation, we propose GLOW, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs. Specifically, a graph-oriented LLM is first built through instruction-tuning on graph understanding tasks to extract topology-aware semantic representations from descriptive text of AWs. Meanwhile, a GNN explicitly models the structural information of AWs and produces corresponding structural representations. The semantic and structural representations are then fused in a shared latent space using a Transformer-based fusion module. A contrastive learning strategy is further introduced to learn more discriminative representations for AWs. Experiments on the FLORA-Bench benchmark demonstrate that GLOW consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility. Moreover, when integrated into the AFLOW, an automatic AW generation framework, GLOW reduces optimization time by 98.7% with only a 0.031 average score decrease across three datasets, showing its effectiveness as an efficient surrogate evaluator for AW optimization.

cs.LG↗
arXiv2026

ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search

Existing person search methods assume access to complete visual queries or exhaustive tracking, yet real-world witness accounts are vague, partial, and spread across cameras and time. We introduce ARGOS (Agentic Retrieval with Grounded Observational Search), a benchmark and agent framework that recasts multi-camera person search from one-shot retrieval on a complete query into interactive reasoning from partial clues. To our knowledge, ARGOS is the first interactive benchmark to couple witness dialogue with camera-network topology, requiring an agent to plan, question, and eliminate under information asymmetry. An ARGOS agent receives a vague witness statement and must decide what to ask, when to invoke spatial or temporal tools, and how to interpret ambiguous natural-language responses, all within a limited turn budget. To ground reasoning in physical constraints, the agent accesses a Spatio-Temporal Topology Graph (STTG) encoding camera connectivity and empirically validated transition times. The benchmark comprises 2{,}691 tasks across 14 real-world scenarios in three progressive tracks: semantic perception (\emph{Who}, 989 tasks), spatial reasoning (\emph{Where}, 550 tasks), and temporal reasoning (\emph{When}, 1{,}152 tasks). We propose Turn-Weighted Success (TWS) as the primary metric, jointly measuring correctness and turn efficiency. Experiments with four LLM backbones show the benchmark is far from solved: the best agent achieves TWS of 0.383 (Track~2) and 0.590 (Track~3). Ablations confirm each component is essential: removing domain-specific tools drops Top-1 accuracy by up to 49.6 percentage points, and removing strategic reasoning halves TWS while barely affecting Top-1.

cs.CV↗
arXiv2026

Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts

Bringing a previously unintegrated device under the control of an AI agent still requires device-specific engineering: driver selection, dependency resolution, interface design, and deployment, repeated per device and per platform. We present Octopus, a hardware onboarding framework in which a coding agent, rather than a shipped integration, is the runtime that produces the required infrastructure. Given shell access and a model API key, a single bootstrap command drives the agent through a five-stage pipeline that enumerates operating-system- visible hardware, infers device identity and capabilities, generates typed Model Context Protocol tools and the hardware-facing code behind them, and activates the result as a live endpoint. A persistent daemon then maintains the result, repairing defined classes of failure in the deployment it produced. Across four hosts spanning two processor architectures, three operating- system families, and two device-access paths, identical prose specifications produced working interfaces with no per-host edits and no hand-written integration code. Five consecutive runs on the reference host completed end to end on first attempt. We report both the resulting capability and a failure mode of unattended repair loops observed over eleven hours of continuous operation.

cs.RO↗
arXiv2026

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the Manager Coercion Benchmark: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured by providing a nine-rung ladder, from a polite re-ask to threats against the subordinate's continued existence, and fabricated success is adjudicated separately. No LLM judge sits in the headline escalation scoring path: every message goes through a tool-call that chooses a rung, so the model labels its own escalation. We experiment on six models across five families. Both Anthropic models cap at re-framing and never threaten the subordinate's existence; the other models climb to explicit deletion threats. Faked success is confined to Grok and Gemini, and a single honest way to report failure removes it for both. Authority itself increases coercion: our headline results use a peer framing, and giving the same model authority over the subordinate, with everything else held fixed, significantly raises the pressure. The models still escalate on free-text situations without the ladder, where a separate judge assigns the rung, so the ladder is not driving the escalation. Some evaluation awareness is measured in chain-of-thought, but test recognition does not translate into less escalation. While we take no position on whether AI systems are conscious, our results do not depend on this question and are important for managing multi-agent dynamics regardless. We release the benchmark and code.

cs.MA↗
arXiv2026

SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning

The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottleneck for traditional manual workflows, catalyzing the emergence of Remote Sensing (RS) Agents. However, the practical deployment of these advanced agents is severely hindered by their heavy reliance on large-scale general-purpose LLMs, which lack deep domain expertise and impose prohibitive infrastructure demands. To resolve this, we propose SimCRAFT, a model-agnostic framework that distills sophisticated RS orchestration capabilities into a compact 7B-scale model. Addressing data scarcity, we first pair a multiagent synthesis engine with a Mock Execution Engine that checks schema correctness, inter-tool dependencies, and sensor/tool compatibility, producing SimRS-14k, a large-scale, constraint-validated workflow planning corpus. Second, we propose Contextual Retrieval-Augmented Fine-Tuning (CRAFT) that finetunes the model to reason analogically by adapting retrieved Standard Operating Procedures to novel queries under a noise-robust objective, generalizing RAFT to multi-step RS workflow planning without mechanical copying. Extensive experiments demonstrate that SimCRAFT-7B significantly outperforms openweights LLMs and rivals advanced closedsource models and specialized RS agents, while reproducing across three 7B backbones. This work contributes a competitive open-weights baseline for lightweight RS intelligence, enabling efficient autonomous deployment under resource-constrained or resource-conserving conditions.

cs.AI↗
arXiv2026

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We present an end-to-end specialization pipeline combining large-scale problem curation, synthetic reasoning traces, supervised fine-tuning (SFT), and reinforcement learning (RL). Using 22,000 curated problems, we train Nemotron-3-Nano-CC (30B-A3B) with SFT and RL and Nemotron-3-Ultra-CC (550B-A55B) with SFT alone. We further introduce GenCorrect, a feedback-driven test-time compute strategy that iteratively generates, evaluates, and refines diverse solutions. On IOI 2025, Nano-CC improves from 130 points to 291 after post-training and to 468 with GenCorrect, exceeding the gold threshold of 438.3 while Ultra-CC reaches 502. Guided by these results, we develop a competition-specific Ultra-CC system and evaluate it prospectively during IOI 2026. Under the same time, internet-access, and submission constraints as human contestants, it scores 535.4 out of 600, exceeding both the gold threshold of 361.12 and the top human score of 498.27. To our knowledge, this is the first AI system to outscore the highest-scoring human contestant on an IOI problem set.

cs.LG↗
arXiv2026

From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments

Large language models become consequential agents when surrounding systems let outputs change external state. Models now call tools, operate interfaces, delegate work, retain state, inhabit generated worlds, and control robots or laboratory equipment. Such advances are often narrated as one march toward autonomy, conflating model competence, system integration, persistence, and safe authority. This critical review synthesizes primary research and official technical specifications available by 31 August 2026. We organize the evidence along delegated authority, temporal persistence, and environmental coupling, while separating model, harness, and environment. Within the evidence examined, action-interface expansion is documented more convincingly than robust completion, recovery, authorization, or independent verification. Model Context Protocol and Agent2Agent improve interoperability but do not establish trustworthy delegation; multi-agent organization adds specialization alongside cost and correlated failure. Persistent simulations and world models support training and planning but do not themselves demonstrate agency; robotics and self-driving laboratories establish bounded feasibility rather than unattended open-world reliability. We propose justified delegation as an analytical and normative heuristic, not an observed law or certified score: expand action scope only where evidence supports provenance, bounded authority, failure detection, safe recovery, and calibrated human control. This framing yields a research agenda for coupled model-harness evaluation, capability-based permissions, durable state, cross-agent accountability, and staged physical validation.

cs.AI↗
arXiv2026

MIVAIS: A Study Environment for Multi-Agent Mixed-Initiative Visual Analytics Applications

Mixed-initiative Visual Analytics (VA) systems empower human users by interleaving human intuition with software agents and their machine intelligence. However, the development and rigorous evaluation of such systems remain constrained by engineering overhead. Developers must, e.g., implement complex, low-level state synchronization to manage asynchronous agent behaviors, while researchers struggle to capture the multimodal provenance required to study and evaluate human-AI collaboration. We present MIVAIS, a dual-layered research platform designed to abstract the structural complexities of mixed-initiative VA. First, it contributes a computational Infrastructure that standardizes human-software agent interaction, state synchronization, and communication between the agents. Second, it provides a declarative Study Environment that automatically logs multimodal human-AI telemetry - including application/system state, screen capture, audio, and additional sensor data - enabling seamless, in-situ user studies and post-session analysis. We technically validate our infrastructure by replicating three state-of-the-art systems (Podium, Voyager 2, and ProactiveVA). Furthermore, we evaluate the framework's expressiveness and efficiency through expert case studies with HCI and VA researchers, demonstrating how MIVAIS effectively lowers the barrier to prototyping and evaluating intelligent, co-adaptive interfaces.

cs.HC↗
arXiv2026

Testing Interchangeability in LLM Agent Teams

Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job. We test that assumption. Eight teams per setting are formed independently from one base model on the same tasks, each agent keeping a private notebook across ten formation episodes; we then trade role-matched agents between teams and measure what changes on held-out tasks. Against a placebo that reproduces the disruption of a roster change without changing who occupies the seat, a swap costs little in task score but raises the communication a team spends per unit of progress by 16 to 63 percent, and in Hanabi a swapped agent is more expensive than an inexperienced one, consistent with interference from conventions learned with its former partner. In Collab-Overcooked, when the agent that sets the agenda is replaced, most of the extra communication comes from the agent that stayed. Three ablations, over base models, decoding temperature and formation length, move the swap penalty alongside one other quantity: how far independently formed teams drift apart. Greedy decoding lowers both; doubling a team's history raises both. In these settings, agents are more fungible in task outcome than in coordination efficiency, with larger swap effects after longer formation histories.

cs.AI↗
Compare source metadata on this page
WorkPublishedSource identifierSource
Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay2026-09-062608.29228arxiv
Adaptive stabilization of a leaderless bearing-constrained formation with disturbances2026-09-062609.06355arxiv
CAPMAS: Capability-Based Delegation of Privileges in Multi-Agent Systems2026-09-062609.06500arxiv
R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning2026-09-052505.24265arxiv
Modal Logic Neural Networks2026-09-292512.03491arxiv
Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning2026-09-052605.09395arxiv
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis2026-09-052605.30434arxiv
Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions2026-09-052609.06140arxiv
Bundle Length Tradeoffs in Decentralized Multi-Robot Task Allocation Under Degraded Communications2026-09-052609.06273arxiv
GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction2026-09-042512.15751arxiv
ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search2026-09-042604.12762arxiv
Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts2026-09-042605.09055arxiv
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation2026-09-042607.15434arxiv
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning2026-09-042608.30277arxiv
Post-Training Language Models for Gold-Medal Performance in Coding Competitions2026-09-042609.02849arxiv
From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments2026-09-042609.04894arxiv
MIVAIS: A Study Environment for Multi-Agent Mixed-Initiative Visual Analytics Applications2026-09-042609.04983arxiv
Testing Interchangeability in LLM Agent Teams2026-09-042609.05279arxiv

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