EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts without updating LLM parameters, either to improve accuracy or to reduce cost. EMAS converts traces into structured diagnoses that specify a revision operation and target. It generates a candidate revision only when the same diagnosis recurs across samples and applies it only if paired validation against the current MAS meets the corresponding acceptance criterion. Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones and is best or tied in six of eight model--benchmark settings. Within two evolution epochs, EMAS achieves relative gains of 6.30% and 20.10% in task-weighted accuracy on Kimi-K2-6 and Qwen3.6-27B, respectively. On MBPP with Qwen3.6-27B, EMAS raises accuracy from 55.09% to 89.12% while reducing token use per task by 62.2%. These results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts.

Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?

Large language model (LLM) agents increasingly rely on skills, structured documents that specify when to act, which procedure to follow, and which tools are allowed. Existing evaluations mostly judge the quality of a skill or its contribution to task success, leaving unexamined whether an agent can recognize a relevant skill and apply it on its own. We introduce Skill-Use, a benchmark that evaluates skill use under progressive disclosure, where an agent sees only a skill's name and short description and must retrieve the full procedure before following it. Skill-Use separates three facets of skill use. Trigger measures whether the agent invokes the relevant skill, Compliance measures how faithfully it follows the prescribed procedure, and Boundary measures whether it avoids forbidden operations. A Skill-Use (SU) score combines the three and credits execution only after the skill is triggered. Skill-Use pairs 79 real skills with 177 executable tasks across nine domains, each grounded in real files, run in an isolated Docker sandbox, and scored by a trajectory-based rubric. Evaluating eight LLMs under two agent harnesses, we find that reliable skill use remains out of reach, as the strongest configuration reaches an SU of only 0.613. Triggering and procedural compliance fail as independent bottlenecks, and both scores and model rankings shift with the harness, so skill use behaves as a capability conditioned on the harness rather than a fixed property of the model.

From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models

Large language model (LLM) evaluation spans diverse tasks and benchmarks, yet evidence remains organized around tasks rather than the capabilities they probe. This fragmentation limits cross-study comparison, obscures capabilities tasks recruit, and makes coverage gaps difficult to identify. We introduce a multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers. Human cognitive science guides capability definition and organization, not LLM architecture. Layer assignments draw on developmental precedence and hypothesized functional support, while human-origin constructs are adapted to observable model behavior. To demonstrate operational utility, we screened 31,505 papers from ACL, AAAI, ICML, and NeurIPS between 2023 and 2025 and mapped 15,934 LLM-focused papers through multi-model annotation, consensus, and arbitration. Direct research attention concentrated on Language-Semantic Competence (3,551; 22.3%), Reasoning (3,388; 21.3%), Planning and Decision-Making (2,149; 13.5%), and Perception (1,954; 12.3%), whereas six domains appeared in fewer than 2% of papers. Within domains, the most frequent subskill had a median prevalence of 97.9% and appeared in at least 90% of papers in 10 of 14 domains. Language-Semantic Competence and Reasoning formed the highest-volume pair (n = 1,864; 11.7%; lift = 2.47), whereas Theory of Mind and Social Reasoning and Interaction showed the highest lift among pairs with at least 20 co-occurrences (n = 62; lift = 30.84). By shifting the unit of analysis from isolated tasks to structured capabilities, the taxonomy supports research organization, coverage audits, evaluation interpretation, and testable hypotheses for diagnosis, training, and transfer.

When RAG Meets Query Planning: Logical Query Trees for Resolving Exploratory Reasoning Problems

Retrieval-Augmented Generation (RAG) effectively grounds large language models (LLMs) in external knowledge but struggles with \textbf{exploratory reasoning problems (ERPs)} that are the complex queries involving high uncertainty and ambiguity. Resolving ERPs requires complex reasoning with unclear paths, tending to result in retrieval noise and error accumulation. Furthermore, the absence of an end-to-end planning mechanism makes it difficult to generate effective trajectories for ERPs. Motivated by database query planning, we introduce \emph{PlanRAG}, an RAG framework that models ERPs of natural language as \textbf{logical query trees (LQTs)}. However, translating ERPs into LQTs is non-trivial due to representation and optimization gaps between structured SQL and unstructured natural language, making it highly challenging to construct high-quality LQTs. To address these problems, we first decompose ERPs into atomic queries and then organize them into LQTs using dynamic programming guided by a cost model involving multiple complementary dimensions. Finally, we execute iterative aggregation, rewriting, retrieval, and generation over LQTs, processing nodes concurrently and propagating intermediate results upward, with further parallelization across multiple threads for efficiency. Our experimental results show that PlanRAG outperforms state-of-the-art iteration-based and graph-based RAG systems on our newly constructed dataset, \textbf{WikiWeb-ERP}, thereby providing a new formulation for optimizing natural language queries. Our source code and dataset are available at https://anonymous.4open.science/r/PlanRAG-main-B2C8/.

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models

Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability. We identify the root cause as sequence-level coupling between efficiency incentives and correctness optimization, which implicitly penalizes long but correct reasoning trajectories. To address this issue, we propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training. ADaPT introduces a mode-selection token to control fast and slow reasoning, applying efficiency-related rewards exclusively to this token to avoid penalizing correct long reasoning while encouraging efficiency when appropriate. Moreover, ADaPT enables precise and continuous control over the efficiency-performance trade-off at inference time: by adjusting the generation probability of the mode-selection token, a single trained model can smoothly move along the efficiency-performance Pareto frontier. Extensive experiments demonstrate that ADaPT significantly reduces inference cost while maintaining strong reasoning performance across multiple benchmarks.

Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design

Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the choice of transition kernels, and poorly designed kernels can lead to issues like training instability, slow convergence, and biased sampling. In this paper, we study this sensitivity through a principled analysis of generalization error and identify three critical factors: asymptotic bias (difficulty in approximating the posterior distribution), exposure bias (error propagation during sampling), and optimization variance induced by kernel dispersion. We further compare different transition kernels: masking diffusion yields sparse and easier posterior-approximation targets, while uniform diffusion provides stronger sampling-side repair but induces harder approximation. Motivated by this trade-off, we revisit a previously overlooked variant, semantic DLM (SemDLM), where the transition kernel corrupts tokens to neighborhoods that are semantically similar. Our theory suggests that SemDLM can serve as a plausible middle ground by reducing the posterior approximation difficulty of uniform diffusion while retaining repair ability. However, we find that SemDLM suffers from a semantic basin problem, where sampling repeatedly stays within a semantic region and produces low-diversity text. To address this, we propose SemDLM+, which adds a global transition and a semantic-frequency penalty during sampling. Experiments on LM1B and OpenWebText show that SemDLM+ improves training dynamics and achieves competitive language modeling and generation quality with satisfactory diversity.

Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models often produce correct answers from flawed reasoning, while struggling to extract consistent rules across demonstrations. This gap is further exacerbated by two visual-level obstacles: an overwhelming proportion of redundant visual tokens that obscure textual cues, and a skewed attention distribution that favors the initial image at the expense of subsequent context. To address these issues, we introduce a framework that restructures multimodal ICL as a principled inductive-deductive process. The framework incorporates a similarity-based visual token compression module to filter out redundant patches, a dynamic attention rebalancing mechanism to distribute focus equitably across all images, and a chain-of-thought paradigm that explicitly guides the model to analyze individual examples, derive a generalizable rule, and then apply it to the query. An auxiliary learning pipeline combines supervised fine-tuning with reinforcement learning using verifiable rewards to reinforce faithful citation and noise filtering. Evaluations across eight benchmarks covering visual perception, logical reasoning, STEM problems, and sarcasm detection demonstrate consistent and significant improvements over standard ICL baselines for multiple open-source VLMs, highlighting the potential of equipping models with genuine inductive capabilities in multimodal settings.

On the Trainability of Masked Diffusion Language Models via Blockwise Locality

Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study blockwise MDMs and compare them with AR-LLMs on three controlled tasks that stress different aspects of structured generation: in-context linear regression, graph path-finding, and Sudoku solving. We find that standard random-masking MDMs fail to reliably learn linear regression, exhibit high variance training dynamics on graph path-finding, while outperforming AR-LLMs on Sudoku. To mitigate these instabilities, we propose two locality aware blockwise models, namely Jigsaw and Scatter, that inject left-to-right inductive bias by enforcing autoregressive locality within blocks while preserving iterative refinement at the block level. Empirically, Jigsaw matches AR-LLM stability on linear regression and remains strong on Sudoku, while Scatter retains diffusion's planning advantage on path-finding. Our results indicate that standard random-masking MDMs, even with blockwise variants, may be a suboptimal instantiation of diffusion LMs for ordered generation, motivating models beyond random masking.

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models

Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current benchmarks face three critical limitations: (1) fragmented evaluation dimensions that often neglect deep cultural nuances; (2) insufficient language coverage in subjective tasks relying on low-quality machine translation; and (3) shallow analysis that lacks diagnostic depth beyond simple rankings. To address these, we introduce GaoYao, a comprehensive benchmark with 182.3k samples, 26 languages and 51 nations/areas. First, GaoYao proposes a unified framework categorizing evaluation tasks into three cultural layers (General Multilingual, Cross-cultural, Monocultural) and nine cognitive sub-layers. Second, we achieve native-quality expansion by leveraging experts to rigorously localize subjective benchmarks into 19 languages and synthesizing cross-cultural test sets for 34 cultures, surpassing prior coverage by up to 111%. Third, we conduct an in-depth diagnostic analysis on 20+ flagship and compact LLMs. Our findings reveal significant geographical performance disparities and distinct gaps between tasks, offering a reliable map for future work. We release the benchmark (https://github.com/lunyiliu/GaoYao).

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, failing to accumulate experience across task boundaries. This paper presents the first formal definition of the Self-Evolving Agent (SEA), formalizes the Evolutionary Flywheel as its minimal sufficient architecture, and introduces SEA-Eval -- the first benchmark designed specifically for evaluating SEAs. Grounded in Flywheel theory, SEA-Eval establishes $SR$ and $T$ as primary metrics and enables through sequential task stream design the independent quantification of evolutionary gain, evolutionary stability, and implicit alignment convergence. Empirical evaluation reveals that under identical success rates, token consumption differs by up to 31.2$\times$ across frameworks, with divergent evolutionary trajectories under sequential analysis -- demonstrating that success rate alone creates a capability illusion and that the sequential convergence of $T$ is the key criterion for distinguishing genuine evolution from pseudo-evolution.