Large Language Models (LLMs) are strong at multi-step reasoning, but running them for every generated token is expensive. Small language models (SLMs) are much cheaper, yet less reliable at the hardest reasoning steps. Existing routing methods mostly make a single query-level decision, assuming that response difficulty is uniform once decoding begins. For chain-of-thought reasoning, however, difficulty varies during generation, making token-level routing a more appropriate granularity. This setting introduces three challenges: token-level uncertainty is noisy, local routing decisions must satisfy global efficiency constraints, and frequent switching can disrupt reasoning coherence. We present TokenRouter, a black-box runtime controller for uncertainty-guided token-level routing between small and large language models. TokenRouter combines a robust entropy detector, a self-calibrating control policy, and a dynamic intervention commitment mechanism for stable switching over difficult spans. Across three reasoning benchmarks, TokenRouter maintains over 99% of pure-LLM accuracy while reducing large-model activation to 56.2%–76.0% of generated tokens. Code is available at https://github.com/sznnzs/TokenRouter.

Text embeddings in RAG indexes, vector stores, and agent memories are rarely leaked as isolated vectors: they often appear with document IDs, chunk offsets, and preserved order. This paper shows that such ordered provenance is not passive metadata but an active privacy channel. We introduce MIRAGE, a public-shadow, zero-victim-pair attack that exploits ordered document-chunk leakage by turning facts recovered from earlier chunks into encoder-verified anchors for later reconstruction. MIRAGE builds public-shadow single-chunk candidates, extracts typed anchors, verifies them with counterfactual encoder-support checks, and uses verified memory to regenerate document-consistent chunks. Across five dense encoders and four decoders on ordered Enron and synthetic CanaryDocs, under a strict 512-query victim-time budget per chunk, MIRAGE outperforms strong fixed-bank reranking, improving macro privacy-unit recall by 5.65-6.10 points across encoders and 5.2-6.9 points across decoders; gains persist (+3.7-4.4 points) on two real, non-templated corpora. Its support check raises accepted-anchor precision from 43.6% to 69.4%, and 34.8% of newly recovered privacy units appear only in regenerated candidates absent from every fixed bank. These results reveal document grouping, chunk order, and offsets as sensitive attack surfaces that RAG and vector-store deployments must protect alongside embeddings themselves.

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying on static visual encodings and lacking the ability to actively verify fine-grained visual evidence, which often leads to speculative reasoning in visually ambiguous cases. We propose V-Retrver, an evidence-driven retrieval framework that reformulates multimodal retrieval as an agentic reasoning process grounded in visual inspection. V-Retrver enables an MLLM to selectively acquire visual evidence during reasoning via external visual tools, performing a multimodal interleaved reasoning process that alternates between hypothesis generation and targeted visual verification. To train such an evidence-gathering retrieval agent, we adopt a curriculum-based learning strategy combining supervised reasoning activation, rejection-based refinement, and reinforcement learning with an evidence-aligned objective. Experiments across multiple multimodal retrieval benchmarks demonstrate consistent improvements in retrieval accuracy (with 23.0% improvements on average), perception-driven reasoning reliability, and generalization.

KV cache compression is critical for long-context LLM inference, yet existing training-free methods fall into a dilemma: attention-based eviction clusters retained tokens around semantically “hot” regions, creating context holes that degrade long-range reasoning, while diversity-based selection retains directionally broad but semantically irrelevant tokens. We identify the root cause: at prefill time, future decoding queries are unknown, making query-conditioned signals unreliable as a sole selection criterion. The retained KV set must instead provide broad directional coverage of the context—so that arbitrary future queries can find supporting keys—while filtering out tokens that expand the coverage span without contributing to generation. We propose AnchorKV, which realizes this principle through block-wise partitioning with uniform per-block budgets and anchor-driven cosine dissimilarity scoring for linear-time diversity estimation. A compression-rate adaptive hybrid score dynamically reweights diversity and importance. Experiments on LongBench across three model families show AnchorKV consistently outperforms existing training-free methods, with the largest margins at low retention ratios. A query-subsampled variant reduces prefill latency by up to 2.7× with minimal accuracy loss. We provide theoretical guarantees on approximation error and variance reduction.

Large Reasoning Models (LRMs) show remarkable capabilities in complex reasoning tasks through Chain-of-Thought (CoT) mechanisms. However, their reasoning processes frequently suffer from overthinking, generating inefficient patterns and substantial overhead without improving quality. Existing pruning approaches typically rely on computationally expensive external teacher models or aggregated sequence-level metrics, failing to capture the fine-grained, intrinsic cognitive state of individual reasoning steps. In this paper, we propose ThinkLeap, a novel confidence-guided optimization framework that identifies and retains only critical cognitive leaps within reasoning chains. Our approach is grounded in the observation that a model’s internal confidence dynamics serve as a fine-grained structural signal: rising confidence often reflects evidence accumulation, while declining confidence signals doubt or redundancy. By leveraging these dynamics, ThinkLeap autonomously replaces inefficient steps with ellipsis markers, preserving the logical flow while signaling omitted deliberation. Extensive experiments across three challenging reasoning benchmarks demonstrate that ThinkLeap establishes a new paradigm for efficient reasoning, achieving an average 19.4% reduction in reasoning length while maintaining comparable accuracy.

Large Language Models (LLMs) face significant memory and latency overheads during long-context inference due to the growing KV cache, especially in Knowledge Base Question Answering (KBQA) settings that require support for multiple downstream queries. Query-aware eviction methods do not generalize across queries, while existing query-agnostic approaches rely on a single proxy query, leading to fragile eviction decisions under high eviction ratios. We propose ContrastKV, a robust query-agnostic KV cache eviction algorithm for multi-query generalization. ContrastKV introduces a contrastive signal fusion mechanism that jointly exploits complementary semantic and non-semantic signals. By contrasting semantic consistency with structural robustness, the method constructs a more reliable eviction criterion that alleviates the blind spots of single-query proxies. The framework integrates efficient signal generation, parallel importance scoring, and multi-level fusion across heads and layers. Experiments show that ContrastKV outperforms state-of-the-art methods, retaining up to 92% accuracy with only 20% of the KV cache budget, while reducing decoding latency by approximately 50% and significantly lowering GPU memory usage.

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks through chain-of-thought (CoT) reasoning. However, they suffer from high inference latency due to lengthy reasoning chains. In this paper, we propose SpecCoT, a collaborative framework that combines large and small models for effective yet efficient reasoning. Unlike traditional speculative decoding, which operates at the token level, SpecCoT adopts a step-level verification strategy: the large model first establishes the reasoning direction, and for each intermediate step, the small model generates multiple candidate drafts in parallel. The large model then verifies these drafts, either selecting the most suitable one or rejecting them all and generating its own. SpecCoT approach balances reasoning quality with inference efficiency through fine-grained model cooperation. Experiments across diverse tasks show SpecCoT reduces inference latency by 1.7-4.1× while maintaining comparable accuracy to standard large model inference.

Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for defense, prior researches reveal the possibility of bypassing such defenses through well-designed jailbreak attacks. In this paper, we propose QueryAttack, a novel framework to examine the generalizability of safety alignment. By treating LLMs as knowledge databases, we translate malicious queries in natural language into structured non-natural query language to bypass the safety alignment mechanisms of LLMs. We conduct extensive experiments on mainstream LLMs, and the results show that QueryAttack not only can achieve high attack success rates (ASRs), but also can jailbreak various defense methods. Furthermore, we tailor a defense method against QueryAttack, which can reduce ASR by up to 64% on GPT-4-1106. Our code is available at https://anonymous.4open.science/r/QueryAttack-334B.

Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Code, the first benchmark with difficulty-tiered samples based on a novel Slide Complexity Metric. We introduce SlideCoder, a layout-aware, retrieval-augmented framework for generating editable slides from reference images. SlideCoder integrates a Color Gradient-based Segmentation algorithm and a Hierarchical Retrieval-Augmented Generation method to decompose complex tasks and enhance code generation. We also release SlideMaster, a 7B open-source model fine-tuned with improved reverse-engineered data. Experiments show that SlideCoder outperforms state-of-the-art baselines by up to 40.5 points, demonstrating strong performance across layout fidelity, execution accuracy, and visual consistency. Our code is available at https://github.com/vinsontang1/SlideCoder.

Large language models (LLMs) excel at complex reasoning tasks but often suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates. We present a novel framework for computationally efficient, trustworthy reasoning under uncertainty, introducing two complementary techniques: Diversity-Aware Self-Signal Dilution (DASD) and Convergent Adaptive Weighted Sampling (CAWS). DASD operates in an unsupervised manner to dilute overconfident, semantically redundant reasoning paths, thereby producing better-calibrated internal confidence estimates. CAWS dynamically allocates computational resources at inference time by aggregating these signals and terminating computation once answer dominance and stability are achieved. Comprehensive experiments across three reasoning datasets demonstrate that our approach maintains accuracy levels while achieving over 70% reduction in inference cost, surpassing competitive baselines. Our framework provides a scalable, unsupervised solution for reliable and efficient LLM reasoning.