arXiv:2606. 01490v1 Announce Type: cross Abstract: We present a controlled experiment evaluating 12 multi-agent LLM collaboration topologies for software architecture design.
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
The paper investigates how scaling a team of small language‑model agents affects performance across different orchestration architectures. By testing eight architectures on five short‑answer benchmarks and an executable‑code benchmark, it finds that team scaling yields large gains on arithmetic word‑problem tasks but only modest improvements on multiple‑choice and code generation tasks, with no single architecture dominating all tasks. The authors explain these patterns using a generate‑transform decomposition that separates coverage and transformation effects, showing that arithmetic tasks benefit from both coverage and critic‑guided transformation, while other tasks are limited by saturation or poor conversion.
MoMHa is a system that optimizes large language model harnesses across three objectives—accuracy, behavioural safety, and token cost—using a single‑phase joint‑reward proposer. It outperforms alternative strategies on seventeen domains, including synthetic suites and real‑world benchmarks, achieving higher joint scores and better safety while reducing token usage. The approach demonstrates that multi‑objective harness design can transfer effectively to unseen models and tasks.
arXiv:2606. 31174v1 Announce Type: new Abstract: Production large language-model (LLM) agents are increasingly deployed not as lone problem-solvers but as managers: a main model creates specialized subagents, delegates work, and orchestrates their parallel, asynchronous returns through dynamic workflows.
AgentAudit is an open, extensible framework that evaluates the full lifecycle of AI agents, assessing planning, tool selection, execution, memory, and reasoning across ten dimensions such as instruction integrity, security, and alignment. Unlike existing benchmarks that focus on single aspects, AgentAudit analyzes the entire execution trace to attribute failures to specific stages. The framework was tested on five large language models, revealing significant differences in trustworthiness even among models with similar task‑completion performance.
arXiv:2609.01437v1 Announce Type: cross Abstract: As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly...
Ideation Arena is a battle-style platform that evaluates research ideas generated by large language models (LLMs) and research agents through pairwise human assessment. The system builds shared literature contexts, collects over 6,000 double-blind comparisons from 105 computer science researchers, and constructs an Elo rating leaderboard to rank proposal-stage expert preferences. It also introduces Ideation Arena Eval, a benchmark to test whether automated evaluators align with human preferences, finding that current LLM judges achieve at best 72.56% Soft Accuracy on overall quality.
RankEvolve is an auto‑research framework that evolves generative ranking models by orchestrating multiple large‑language‑model coding agents through an Executable Operating Protocol (EOP). The system compiles a state machine that enforces phases, gates, branches, and loops, while a meta‑meta‑harness lets agents review and repair each other’s code. In budget‑matched experiments, heterogeneous composition of agents raised execution accuracy from 45.8 % to 62.5 % and reduced silent critical‑defect rates, achieving notable gains on the HSTU recommender and other benchmarks.
arXiv:2606. 00308v1 Announce Type: cross Abstract: Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipelines - and is evaluated almost exclusively on functional correctness.
arXiv:2603. 20324v2 Announce Type: replace-cross Abstract: Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation.
arXiv:2606. 24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real.
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.