The Illusion of Multi-Agent Advantage

Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making. However, empirical support for this claim relies primarily on comparisons with SAS baselines using benchmarks that prioritize isolated reasoning tasks, which do not adequately assess these advantages. Focusing on automatically generated MAS that are designed for enhanced generalizability over manually-designed counterparts, we perform a rigorous, systematic evaluation against SAS, specifically Chain-of-Thought with Self-Consistency (CoT-SC). Across traditional reasoning datasets and tasks with interactive multi-step workflows (e.g., BrowseComp-Plus), we demonstrate that automatic MAS consistently underperform CoT-SC despite being up to 10x more expensive. To isolate these failures from limitations inherent to task structure, we introduce a diagnostic synthetic dataset tailored for MAS featuring explicit task decomposition, context separation and parallelization potential. We show that expert-architected MAS consistently outperforms automatically generated architectures in both raw performance and cost-efficiency on this dataset, demonstrating that existing evaluation frameworks mask critical architectural gaps and inefficiencies of complex MAS by failing to account for the marginal utility of increased computational cost. Critically, systematic deconstruction of the generated MAS architectures reveals that current automated design paradigms produce architectural bloat that prioritizes superficial complexity which does not translate into functional utility, exposing a fundamental misalignment with multi-agent principles.

Reward Modeling for Multi-Agent Orchestration

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by limited supervision and high computational cost. We propose Orchestration Reward Modeling (OrchRM), a self-supervised framework for evaluating orchestration quality without human annotations. OrchRM leverages intermediate artifacts from multi-agent executions to construct win-lose pairs for Bradley-Terry reward model training. Unlike existing MAS test-time scaling and orchestrator training frameworks that rely on costly sub-agent rollouts, OrchRM operates directly at the orchestration level, enabling efficient and high-performing reward-guided orchestrator training and MAS test-time scaling. OrchRM improves training efficiency by up to 10x in token usage while improving MAS test-time scaling performance by up to 8% in accuracy. These gains consistently transfer across multiple domains, including mathematical reasoning, web-based question answering, and multi-hop reasoning, demonstrating orchestration-level reward modeling as a scalable direction for robust multi-agent orchestration. Code will be available at https://github.com/Wang-ML-Lab/OrchRM.

The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering

Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they may be under-critical and miss erroneous steps, or over-critical and reject correct reasoning. We refer to this tendency to be overly lenient or overly critical as verifier strictness. In this work, we study whether verifier strictness can be controlled through hidden-state intervention. We uncover a verification-specific hidden-state signal: in step-wise verification, a verifier's tendency to accept or reject a solution step is encoded near the boundary of the corresponding verification paragraph. Exploiting this signal, we show that hidden-state steering can directly modulate verifier strictness without fine-tuning. However, uniform steering induces a trade-off between error detection and correctness certification. To address this, we propose VerifySteer, which exploits latent correctness signals for sample-level routing and selectively intervenes on paragraph boundaries. Experiments on ProcessBench and Hard2Verify show that VerifySteer outperforms prompt optimization and activation steering baselines, and is competitive with self-consistency while requiring 4-7x less inference compute. VerifySteer is also complementary to verification fine-tuning, providing further gains on top of fine-tuned verifiers. The code is available at https://github.com/YefanZhou/VerifySteer.

DATAREEL: Automated Data-Driven Video Story Generation with Animations

Data videos are a powerful medium for visual data based storytelling, combining animated, chart-centric visualizations with synchronized narration. Widely used in journalism, education, and public communication, they help audiences understand complex data through clear and engaging visual explanations. Despite their growing impact, generating data-driven video stories remains challenging, as it requires careful coordination of visual encoding, temporal progression, and narration and substantial expertise in visualization design, animation, and video-editing tools. Recent advances in large language models offer new opportunities to automate this process; however, there is currently no benchmark for rigorously evaluating models on animated visualization-based video storytelling. To address this gap, we introduce DataReel, a benchmark for automated data-driven video story generation comprising 328 real-world stories. Each story pairs structured data, a chart visualization, and a narration transcript, enabling systematic evaluation of models' abilities to generate animated data video stories. We further propose a multi-agent framework that decomposes the task into planning, generation, and verification stages, mirroring key aspects of the human storytelling process. Experiments show that this multi-agent approach outperforms direct prompting baselines under both automatic and human evaluations, while revealing persistent challenges in coordinating animation, narration, and visual emphasis. We release DataReel at https://github.com/vis-nlp/DataReel.

Lost in Translation: Do LVLM Judges Generalize Across Languages?

Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric benchmarks, leaving open the question of how well these evaluators generalize across languages. To answer this question, we introduce MM-JudgeBench, the first large-scale benchmark for multilingual and multimodal judge model evaluation, which includes over 60K pairwise preference instances spanning 25 typologically diverse languages. MM-JudgeBench integrates two complementary subsets: a general vision-language preference evaluation subset extending VL-RewardBench, and a chart-centric visual-text reasoning subset derived from OpenCQA, enabling systematic analysis of reward models (i.e., LVLM judges) across diverse settings. We additionally release a multilingual training set derived from MM-RewardBench, disjoint from our evaluation data, to support domain adaptation. By evaluating 22 LVLMs (15 open-source, 7 proprietary), we uncover substantial cross-lingual performance variance in our proposed benchmark. Our analysis further shows that model size and architecture are poor predictors of multilingual robustness, and that even state-of-the-art LVLM judges exhibit inconsistent behavior across languages. Together, these findings expose fundamental limitations of current reward modeling and underscore the necessity of multilingual, multimodal benchmarks for developing reliable automated evaluators.

VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?

As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software engineering yet never systematically evaluated. We present \name{}, the first empirical decomposition that jointly evaluates two coupled tasks: \emph{Fault-Triggering Test Generation (FT-Test)} constructing a discriminative witness that exposes a latent bug, and \emph{Fault-targeted Program Repair (FPR)}, repairing it under varying diagnostic conditions. \name{} pairs competitive programming problems with LLM-generated solutions that pass partial test suites but fail on semantic edge cases, enabling controlled identification of where the diagnostic chain breaks down. Evaluating 12 frontier LLMs, we find that fault-targeted reasoning does not scale with general coding ability. Models produce syntactically valid test inputs at near-ceiling rates yet collapse on discriminative generation, with fault hypothesis generation -- not output validation -- as the dominant bottleneck. Test-guided repair reveals a complementary insight: when self-generated tests successfully witness a fault, the resulting repair matches or outperforms repair guided by externally provided tests, but tests that fail to witness the fault actively degrade repair below unguided baselines. Together, these results reframe the challenge of autonomous debugging: the binding bottleneck is not code synthesis or test validity but fault-target reasoning, a capability that remains deficient across all frontier models. As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software engineering yet never systematically evaluated.

SkillOrchestra: Learning to Route Agents via Skill Transfer

Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two limitations: (1) input-level routers make coarse query-level decisions that ignore evolving task requirements; (2) RL-trained orchestrators are expensive to adapt and often suffer from routing collapse, repeatedly invoking one strong but costly option in multi-turn scenarios. We introduce SkillOrchestra, a framework for skill-aware orchestration. Instead of directly learning a routing policy end-to-end, SkillOrchestra learns fine-grained skills from execution experience and models agent-specific competence and cost under those skills. At deployment, the orchestrator infers the skill demands of the current interaction and selects agents that best satisfy them under an explicit performance-cost trade-off. Extensive experiments across ten benchmarks demonstrate that SkillOrchestra outperforms SoTA RL-based orchestrators by up to 22.5% with 700x and 300x learning cost reduction compared to Router-R1 and ToolOrchestra, respectively. These results show that explicit skill modeling enables scalable, interpretable, and sample-efficient orchestration, offering a principled alternative to data-intensive RL-based approaches. The code is available at: https://github.com/jiayuww/SkillOrchestra.

References Improve LLM Alignment in Non-Verifiable Domains

While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking ground-truth verifiers, such as LLM alignment. In this work, we investigate whether reference-guided LLM-evaluators can bridge this gap by serving as soft "verifiers". First, we design evaluation protocols that enhance LLM-based evaluators for LLM alignment using reference outputs. Through comprehensive experiments, we show that a reference-guided approach substantially improves the accuracy of less capable LLM-judges using references from frontier models; stronger LLM-judges can also be enhanced by high-quality (i.e., human-written) references. Building on these improved judges, we demonstrate the utility of high-quality references in alignment tuning, where LLMs guided with references are used as judges to self-improve. We show that reference-guided self-improvement yields clear gains over both direct SFT on reference outputs and self-improvement with reference-free judges, achieving performance comparable to training with ArmoRM, a strong finetuned reward model. Specifically, our method achieves 73.1% and 58.7% on AlpacaEval and Arena-Hard with Llama-3-8B-Instruct, and 70.0% and 74.1% with Qwen2.5-7B, corresponding to average absolute gains of +20.2 / +17.1 points over SFT distillation and +5.3 / +3.6 points over reference-free self-improvement on AlpacaEval / Arena-Hard. These results highlight the potential of using reference-guided LLM-evaluators to enable effective LLM post-training in non-verifiable domains.

Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource consumption and accelerate inference, it is essential to eliminate redundant parameters without compromising performance. However, conventional pruning methods that directly remove such parameters often lead to a dramatic drop in model performance in reasoning tasks, and require extensive post-training to recover the lost capabilities. In this work, we propose a gradual compacting method that divides the compression process into multiple fine-grained iterations, applying a Prune-Tune Loop (PTL) at each stage to incrementally reduce model size while restoring performance with finetuning. This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss. Experimental results show that PTL can compress LLMs to nearly half their original size with only lightweight post-training, while maintaining performance comparable to the original model on reasoning tasks. Moreover, PTL is flexible and can be applied to various pruning strategies, such as neuron pruning and layer pruning, as well as different post-training methods, including continual pre-training and reinforcement learning. Additionally, experimental results confirm the effectiveness of PTL on a variety of tasks beyond mathematical reasoning, such as code generation, demonstrating its broad applicability.

MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning settings, and has been suggested as a potential tool for guiding coordination of MAS; however, its actual effectiveness in MAS remains unclear. To fill this gap, we present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS). Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models), evaluated across two levels of verification granularity (agent-level and iteration-level). We further examine five representative verifiers and four context management strategies, and conduct experiments over six diverse MAS frameworks on multiple reasoning benchmarks. We find that process-level verification does not consistently improve performance and frequently exhibits high variance, highlighting the difficulty of reliably evaluating partial multi-agent trajectories. Among the methods studied, LLM-as-a-Judge generally outperforms reward-based approaches, with trained judges surpassing general-purpose LLMs. We further observe a small performance gap between LLMs acting as judges and as single agents, and identify a context-length-performance trade-off in verification. Overall, our results suggest that effective and robust process verification for MAS remains an open challenge, requiring further advances beyond current paradigms. Code is available at https://github.com/Wang-ML-Lab/MAS-ProVe.