Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity, leading to hallucinations where generated text contradicts the image. Countering this bias typically requires resource-heavy fine-tuning or high-latency verification methods that provide feedback only after the full response is generated. To overcome these limitations, we present a framework for Token-level Inference-Time Alignment (TITA) that steers the decoding process without updating the base model parameters. By training a lightweight reward model to capture visual preferences, TITA extracts implicit guidance through log-probability ratios. This approach functions as an inference-time adaptation of Direct Preference Optimization (DPO), injecting dense feedback to correct the output distribution at every generation step. Across diverse architectures including LLaVA-1.5, Qwen3-VL, and InternVL3.5, TITA consistently improves performance on 13 benchmarks. For example, TITA boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score with Qwen3-VL-8B. Specifically, these gains incur negligible overhead (~0.2s per query), offering a superior trade-off between alignment effectiveness and efficiency. Our code is available at: https://github.com/Thecommonirin/TITA.

Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (*e.g.*, HuggingFace with >2M models) based on natural language requests. Unlike invoking a fixed set of API tools, repository-scale model selection must handle massive, evolving candidates with incomplete metadata. Existing approaches incorporate full model descriptions into prompts, resulting in prompt bloat, excessive token costs, and limited scalability. To address these issues, we propose **HuggingR⁴**, the first framework to recast model selection as an iterative reasoning process rather than one-shot retrieval. By integrating **R**easoning, **R**etrieval, **R**efinement, and **R**eflection, HuggingR⁴ progressively decomposes user intent, retrieves candidates through multi-round deliberation, refines selections via fine-grained analysis, and validates results through reflection. To facilitate rigorous evaluation, we introduce a large-scale benchmark comprising 14,399 user requests across 37 task categories. Experiments demonstrate that HuggingR⁴ achieves 93.01% workability and 84.25% reasonability—outperforming state-of-the-art baselines by absolute margins of 17.81% and 23.13%, respectively, while reducing token consumption by 6.9×.

Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this setting, the useful response is not always refusal: the model should ask for the missing premise, condition its answer on the unknown quantity, or abstain when no informative conditional response is available. We present Ask-Condition-Abstain Reinforcement Learning (ACA-RL), a data-augmented RL framework for this setting. Its reasoning-graph-guided pipeline converts well-posed problems into missing-premise training instances with localized gap annotations; ACA-RL then trains on these instances with a structured reward over five observable response behaviors. We also introduce the Missing-Premise Benchmark (MPB), a 274-instance human-verified benchmark spanning mathematical, logical, and real-world word problems. Across Qwen3 and Llama models, ACA-RL consistently improves on MPB while preserving competitive performance on well-posed reasoning tasks. This work supports a new mission for NLP evaluation: measuring whether models can recognize when a task is underdetermined and handle uncertainty, not only whether they can answer fully specified questions.

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment, they rest upon the implicit assumption that all LoRA matrices contribute constructively to the merged model. In this paper, we uncover a critical bottleneck in current merging paradigms: the existence of negative modules—specific LoRA layers that inherently degrade global performance upon merging. We propose Evolutionary Negative Module Pruning (ENMP), a plug-and-play LoRA pruning method to locate and exclude these detrimental modules prior to merging. By leveraging an evolutionary search strategy, ENMP effectively navigates the discrete, non-differentiable landscape of module selection to identify optimal pruning configurations. Extensive evaluations demonstrate that ENMP consistently boosts the performance of existing merging algorithms, achieving a new state-of-the-art across both language and vision domains. Code is available at https://github.com/CaoAnda/ENMP-LoRAMerging.