Consistency evaluation of benchmarks used for causal discovery

In graphical causal model, causal discovery aims to construct a causal graph based on numerical data and domain knowledge in plain text. However, the evaluation of causal discovery methods remains a challenge in the area as the progress of domain researches often makes benchmark causal graphs contain mis-aligned knowledge. This problem especially affects the evaluation of large language model (LLM) based causal discovery methods as they are sensitive to the new discoveries in the literature. This work is the first to systematically study the quality of benchmark causal graphs. Specifically, we design a pipeline that automatically retrieves relevant research papers from scientific databases, and prompts LLMs to check the consistency between the benchmark causal graphs and domain research papers. We evaluate 11 popular real-world benchmarks, for which our pipeline in total proceeds 38,081 domain papers. Our results show that popular benchmarks vary significantly in their consistency with domain research, with clear implications for causal discovery research.

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation

Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal variants are mostly evaluated on short-form tasks, where outputs end after a few tokens. Extending these methods to long-form generation exposes a fundamental yet underexamined limitation: token-level distillation implicitly treats all output tokens as equally informative, but long-form outputs are dominated by high-frequency template and grammatical tokens, while the tokens that actually determine output quality are sparsely distributed. In medical report generation (MRG), two such decisive tokens stand out: pathology-related tokens that determine diagnostic content, and the end-of-sequence (EOS) event that determines termination. Both receive insufficient supervision under uniform cross-entropy, and autoregressive decoding further compounds the problem by drifting away from teacher-forced trajectories. We propose DIVE, a frozen-backbone distillation framework that addresses long-form report generation through two complementary mechanisms matched to these failures. Decisive-token supervision restores supervision balance by upweighting the cross-entropy contribution of pathology-related tokens and the EOS event, ensuring that content fidelity and termination are learned during training rather than imposed at decoding time. State-conditioned dynamic steering replaces fixed open-loop residuals with hidden-state-dependent adapters, allowing the injected signal to adapt as decoding drifts. Experiments on MIMIC-CXR and CheXpert Plus with two medical VLM backbones show that DIVE consistently ranks among the strongest methods across lexical and clinical-proxy metrics. Our method achieves the best BLEU-4, ROUGE-L, and RadGraph F1 in all dataset--backbone settings, while remaining competitive on coarse label-level CheXbert F1.

Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction

Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, providing a computational route to understanding how perturbations reshape cellular programs over time. Existing machine learning methods have made important progress, but typically capture only one side of the response. Latent causal approaches seek mechanisms that support generalization and interpretation, yet often treat perturbation effects as static outcomes. Temporal models describe how gene expression changes across time, but usually do not explicitly recover the latent causal generative mechanisms driving these changes. In practice, perturbation effects are both latent and dynamical: interventions act through unobserved cellular programs, whose states evolve over time and give rise to observed expression profiles. Motivated by this view, we propose a latent dynamical causal generative model for single-cell perturbation data that jointly captures latent cellular programs, perturbation-conditioned mechanisms, and temporal evolution. We further provide an identifiability analysis showing that, under suitable conditions, the latent causal variables are recoverable up to standard equivalence classes. Guided by this analysis, we develop CITE-VAE, a learning framework for recovering latent cellular programs and their perturbation-driven dynamics from single-cell sequencing data. Experiments on Causal-3DIdent validate the theoretical results and the effectiveness of the proposed method in controlled settings. Additional experiments on real-world CRISPR-based single-cell perturbation data show improved generalization to unseen perturbations compared with state-of-the-art baselines, highlighting the practical robustness of our approach.

What Makes a Representation Good for Single-Cell Perturbation Prediction?

Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approaches, from causal representation learning to foundation models, often struggle with an overlooked challenge: gene expression is dominated by perturbation-invariant information, while perturbation-specific signals are intrinsically sparse. As a result, learned representations either entangle invariant and perturbation-specific information, leading to spurious and non-generalizable predictors, or suppress perturbation-specific signals altogether, rendering them ineffective for prediction. To address this, we propose PerturbedVAE, a general framework designed to resolve this signal imbalance. The framework explicitly separates perturbation-specific information from dominant invariant structure and recovers causal representations to effectively utilize such information for prediction. We further provide an identifiability analysis that characterizes the conditions under which sparse perturbation effects can be reliably recovered, thereby clarifying how the framework can be concretely specified under such conditions. Empirically, PerturbedVAE achieves state-of-the-art performance on a widely used benchmark across multiple evaluation settings, yielding significant gains on out-of-distribution combinatorial predictions and uncovering interpretable perturbation-response programs.

FERA: Uncertainty-Aware Federated Reasoning for Large Language Models

Large language models (LLMs) exhibit strong reasoning capabilities when guided by high-quality demonstrations, yet such data is often distributed across organizations that cannot centralize it due to regulatory, proprietary, or institutional constraints. We study federated reasoning, where a server improves multi-step reasoning by coordinating with heterogeneous clients holding private demonstrations, without centralized training or raw data sharing. The key challenge is that client reliability is query-dependent, while the server cannot inspect client data to determine which contributions are trustworthy. To address this, we propose Uncertainty-Aware Federated Reasoning (FERA), a training-free framework based on iterative server-client co-refinement. Across communication rounds, clients generate reasoning traces with lightweight uncertainty estimates, and the server synthesizes them into improved reasoning that is redistributed as context for the next round, progressively improving both server outputs and client-side reasoning. Within each round, Uncertainty-Aware Self-Critique Aggregation (UA-SCA) resolves conflicts among heterogeneous client traces through query-dependent trust weighting and structured cross-client verification. Rather than simply discarding low-quality traces, UA-SCA revises flawed reasoning steps to recover useful information. We provide theoretical guarantees showing that the proposed iterative protocol converges and that uncertainty-aware weighting accelerates convergence. Experiments on multiple reasoning benchmarks show that FERA consistently outperforms both federated training and training-free baselines, achieving progressively higher accuracy across rounds while maintaining communication and computational efficiency.

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG

Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdated knowledge. However, current MRAG systems struggle to distinguish whether retrieved multimodal data truly supports the semantic core of an answer or merely provides superficial relevance. Existing metrics often rely on heuristic position-based confidence, which fails to capture the informational density of multimodal entities. To address this, we propose Multi-modal Evidence Grounding (MEG), a semantic-aware metric that quantifies the contribution of retrieved evidence. Unlike standard confidence measures, MEG utilizes Semantic Certainty Anchoring, focusing on high-IDF information-bearing tokens that better capture the semantic core of the answer. Building on MEG, we introduce MEG-RAG, a framework that trains a multimodal reranker to align retrieved evidence with the semantic anchors of the ground truth. By prioritizing high-value content based on semantic grounding rather than token probability distributions, MEG-RAG improves the accuracy and multimodal consistency of generated outputs. Extensive experiments on the M$^2$RAG benchmark show that MEG-RAG consistently outperforms strong baselines and demonstrates robust generalization across different teacher models.

Doctor-RAG: Failure-Aware Repair for Agentic Retrieval-Augmented Generation

Agentic Retrieval-Augmented Generation (Agentic RAG) has become a widely adopted paradigm for multi-hop question answering and complex knowledge reasoning, where retrieval and reasoning are interleaved at inference time. As reasoning trajectories grow longer, failures become increasingly common. Existing approaches typically address such failures by either stopping at diagnostic analysis or rerunning the entire retrieval-reasoning pipeline, which leads to substantial computational overhead and redundant reasoning. In this paper, we propose Doctor-RAG (DR-RAG), a unified diagnose-and-repair framework that corrects failures in Agentic RAG through explicit error localization and prefix reuse, enabling minimal-cost intervention. DR-RAG decomposes failure handling into two consecutive stages: (i) trajectory-level failure diagnosis and localization, which attributes errors to a coverage-gated taxonomy and identifies the earliest failure point in the reasoning trajectory; and (ii) tool-conditioned local repair, which intervenes only at the diagnosed failure point while maximally reusing validated reasoning prefixes and retrieved evidence. By explicitly separating error attribution from correction, DR-RAG enables precise error localization, thereby avoiding expensive full-pipeline reruns and enabling targeted, efficient repair. We evaluate DR-RAG across three multi-hop question answering benchmarks, multiple agentic RAG baselines, and different backbone models. Experimental results demonstrate that DR-RAG substantially improves answer accuracy while significantly reducing reasoning token consumption compared to rerun-based repair strategies.

Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding

Existing chemical understanding tasks primarily rely on static molecular representations, limiting their ability to model inherently dynamic phenomena such as bond breaking or conformational changes, which are essential for a chemist to understand chemical reactions. To address this gap, we introduce Chemical Dynamics Understanding (ChemDU), a new task that translates 4D molecular trajectories into interpretable natural-language explanations. ChemDU focuses on fundamental dynamic scenarios, including gas-phase and catalytic reactions, and requires models to reason about key events along molecular trajectories, such as bond formation and dissociation, and to generate coherent, mechanistically grounded narratives. To benchmark this capability, we construct Chem4DBench, the first dataset pairing 4D molecular trajectories with expert-authored explanations across these settings. We further propose Chem4DLLM, a unified model that integrates an equivariant graph encoder with a pretrained large language model to explicitly capture molecular geometry and rotational dynamics. We hope that ChemDU, together with Chem4DBench and Chem4DLLM, will stimulate further research in dynamic chemical understanding and multimodal scientific reasoning.

Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering

Automated radiology report generation using vision-language models (VLMs) is limited by the risk of prior-comparison hallucination, where the model generates historical findings unsupported by the current study. We address this challenge with a training-free, inference-time control framework termed Semantically Decoupled Latent Steering (SDLS). Unlike generic activation steering, which often suffers from semantic entanglement, our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition followed by $QR$-based orthogonalization. This orthogonalization step is critical. It leverages geometric constraints to filter out the clinical semantics often entangled in standard principal component analysis (PCA) directions, ensuring that the steering vector targets only the ``historical comparison" axis. We validate our method on the BiomedGPT foundation model, demonstrating that it overcomes the trade-off between hallucination suppression and clinical accuracy. Extensive experiments on MIMIC-CXR, and zero-shot transfer evaluation on CheXpert Plus and IU-Xray, demonstrate the robustness of our approach. Quantitative evaluations on MIMIC-CXR show that our approach significantly reduces the probability of historical hallucinations (FilBERT score decreases from 0.2373 to 0.1889) and improves clinical label fidelity (CheXpert macro-F1 increases from 0.2242 to 0.3208). Supplementary evaluations confirm that the structural integrity of the clinical narrative is maintained.

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to realize relative gains, leading to inefficient reasoning and overthinking, and complicating the trade-off between correctness and rollout efficiency. Controlling this behavior is difficult in practice, considering (i) Length penalties are hard to calibrate because longer rollouts may reflect harder problems that require longer reasoning, penalizing tokens risks truncating useful reasoning along with redundant continuation; and (ii) supervision that directly indicates when to continue or stop is typically unavailable beyond final answer correctness. We propose Weakly Supervised GRPO (WS-GRPO), which improves rollout efficiency by converting terminal rewards into correctness-aware guidance over partial trajectories. Unlike global length penalties that are hard to calibrate, WS-GRPO trains a preference model from outcome-only correctness to produce prefix-level signals that indicate when additional continuation is beneficial. Thus, WS-GRPO supplies outcome-derived continue/stop guidance, reducing redundant deliberation while maintaining accuracy. We provide theoretical results and empirically show on reasoning benchmarks that WS-GRPO substantially reduces rollout length while remaining competitive with GRPO baselines.