RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning

Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL). Successful trajectories are expensive to collect and often contain inefficient detours. After supervised fine-tuning (SFT), full trajectory corpora are dominated by routine states; moreover, when group-relative RL is applied to web actions, inadequately designed action-level rewards can yield weak or misleading relative updates, while groups rejected as unsuitable for such updates receive no fallback learning signal. We present RMSWeb, a three-part recipe for Qwen3-VL-Instruct at 8B and 32B. Reflection-conditioned retries increase collection yield and shorten successful trajectories; failure-mode mining concentrates offline RL on critical states exposed by the SFT policy; and Salvage-DS combines an action-semantic polarized reward, contrast-and-competence-gated dynamic sampling, and an action-only anchor for rejected groups. Policies trained with reflection-collected data use up to 19.7% fewer action steps on solved tasks. On WebVoyager, Online-Mind2Web, and WebTailBench, RMSWeb improves over SFT by 2.4-7.0 points at 8B and 1.2-7.7 points at 32B. Our 8B model also achieves the strongest reported Online-Mind2Web result among similarly sized open-weight models in our comparison and a leading reported accuracy-cost trade-off on WebVoyager and WebTailBench, with the caveat that external evaluation protocols differ.

The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions

Large language models (LLMs) are increasingly deployed as black-box classifiers in pipelines that automate confident decisions and route uncertain ones to human review. Such selective prediction needs a confidence score that an operator can threshold at a chosen risk level. Prior work asks whether LLM confidence is well calibrated or well ranked; we ask a complementary, deployment-oriented question that has been largely overlooked: at what resolution can the score be thresholded? We call the answer the score granularity gap. Through a controlled comparison of seven ways to build a confidence score, from a single verbalized number, to token probabilities, to querying the model many times and combining the answers, across 25 model-dataset pairs (9 LLMs, 3 benchmarks), we find that single-shot verbalized confidence, once correctly converted to a class probability, ranks cases surprisingly well, yet takes only a handful of distinct values. It therefore offers an operator only a few coarse thresholds, no matter how well it ranks. We show which constructions widen this gap, at what inference cost, and with what effect on ranking, notably that multi-query aggregation helps weak models but can degrade already-strong ones. We translate these trade-offs into concrete deployment guidance.

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

Decoding-time truthfulness methods -- layer-contrast decoding, inference-time intervention, and learned logit adapters -- have demonstrated 10-30 point gains on TruthfulQA when applied to base language models. However, modern instruction-tuned LLMs already achieve substantially higher baselines (61-76%), raising the question of whether these methods remain effective in practice. We design a six-control evaluation framework -- out-of-distribution training, multi-judge validation, simple decoding baselines, confound controls, bootstrap confidence intervals, and seed variance -- and apply it across 5 models (1B-70B), 3 benchmarks, and 15 methods. We find that previously reported gains shrink substantially under strict controls: on the full TruthfulQA benchmark (N=817), no token-level method achieves statistically significant improvement, and the best learned adapter scores -2.0 points below greedy (p=.23). We identify five evaluation sensitivities -- contamination, judge choice, missing baselines, confounds, and statistical noise -- that individually or jointly account for these discrepancies. Cross-benchmark validation on HaluEval QA and TriviaQA confirms that these patterns extend beyond TruthfulQA. Deliberative prompting methods (chain-of-thought, self-critique) appear more robust in the evaluated regime, with CoT achieving +5.6-19pp across benchmarks as a training-free, single-pass method. We release a seven-point evaluation checklist and discuss implications for future truthfulness research.

State Rank Dynamics in Linear Attention LLMs

Linear Attention Large Language Models (LLMs) offer a compelling recurrent formulation that compresses context into a fixed-size state matrix, enabling constant-time inference. However, the internal dynamics of this compressed state remain largely opaque. In this work, we present a comprehensive study on the runtime state dynamics of state-of-the-art Linear Attention models. We uncover a fundamental phenomenon termed State Rank Stratification, characterized by a distinct spectral bifurcation among linear attention heads: while one group maintains an effective rank oscillating near zero, the other exhibits rapid growth that converges to an upper bound. Extensive experiments across diverse inference contexts reveal that these dynamics remain strikingly consistent, indicating that the identity of a head,whether low-rank or high-rank,is an intrinsic structural property acquired during pre-training, rather than a transient state dependent on the input data. Furthermore, our diagnostic probes reveal a surprising functional divergence: low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy. Leveraging this insight, we propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9\% reduction in KV-cache overhead while largely maintaining model accuracy.

Spava: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention on a single GPU, yielding limited acceleration or degraded performance and restricting LMMs from handling longer, more complex videos. To overcome these issues, we propose Spava, a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. By distributing approximate attention, Spava reduces computation and increases parallelism, enabling efficient processing of more visual embeddings without compression and thereby improving task performance. System-level optimizations, such as load balancing and fused forward passes, further unleash the potential of Spava, delivering speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB, without notable performance loss. Code available at https://github.com/thunlp/APB

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters

As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism. We demonstrate that dense models, when forced to fit conflicting value distributions, suffer from \textbf{Mean Collapse}, converging to a generic average that fails to represent diverse groups. We attribute this to \textbf{Cultural Sparsity}, where gradient interference prevents dense parameters from spanning distinct cultural modes. To resolve this, we propose \textbf{\textsc{CuMA}} (\textbf{Cu}ltural \textbf{M}ixture of \textbf{A}dapters), a framework that frames alignment as a \textbf{conditional capacity separation} problem. By incorporating demographic-aware routing, \textsc{CuMA} internalizes a \textit{Latent Cultural Topology} to explicitly disentangle conflicting gradients into specialized expert subspaces. Extensive evaluations on WorldValuesBench, Community Alignment, and PRISM demonstrate that \textsc{CuMA} achieves state-of-the-art performance, significantly outperforming both dense baselines and semantic-only MoEs. Crucially, our analysis confirms that \textsc{CuMA} effectively mitigates mean collapse, preserving cultural diversity. Our code is available at https://github.com/Throll/CuMA.

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning

LLM-based translation agents have achieved highly human-like translation results and are capable of handling longer and more complex contexts with greater efficiency. However, they are typically limited to text-only inputs. In this paper, we introduce ViDove, a translation agent system designed for multimodal input. Inspired by the workflow of human translators, ViDove leverages visual and contextual background information to enhance the translation process. Additionally, we integrate a multimodal memory system and long-short term memory modules enriched with domain-specific knowledge, enabling the agent to perform more accurately and adaptively in real-world scenarios. As a result, ViDove achieves significantly higher translation quality in both subtitle generation and general translation tasks, with a 28% improvement in BLEU scores and a 15% improvement in SubER compared to previous state-of-the-art baselines. Moreover, we introduce DoveBench, a new benchmark for long-form automatic video subtitling and translation, featuring 17 hours of high-quality, human-annotated data. Our code is available here: https://github.com/pigeonai-org/ViDove

LLM-Powered CPI Prediction Inference with Online Text Time Series

Forecasting the Consumer Price Index (CPI) is an important yet challenging task in economics, where most existing approaches rely on low-frequency, survey-based data. With the recent advances of large language models (LLMs), there is growing potential to leverage high-frequency online text data for improved CPI prediction, an area still largely unexplored. This paper proposes LLM-CPI, an LLM-based approach for CPI prediction inference incorporating online text time series. We collect a large set of high-frequency online texts from a popularly used Chinese social network site and employ LLMs such as ChatGPT and the trained BERT models to construct continuous inflation labels for posts that are related to inflation. Online text embeddings are extracted via LDA and BERT. We develop a joint time series framework that combines monthly CPI data with LLM-generated daily CPI surrogates. The monthly model employs an ARX structure combining observed CPI data with text embeddings and macroeconomic variables, while the daily model uses a VARX structure built on LLM-generated CPI surrogates and text embeddings. We establish the asymptotic properties of the method and provide two forms of constructed prediction intervals. The finite-sample performance and practical advantages of LLM-CPI are demonstrated through both simulation and real data examples.

MiniCPM4: Ultra-Efficient LLMs on End Devices

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems. Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing. Regarding training data, we propose UltraClean, an efficient and accurate pre-training data filtering and generation strategy, and UltraChat v2, a comprehensive supervised fine-tuning dataset. These datasets enable satisfactory model performance to be achieved using just 8 trillion training tokens. Regarding training algorithms, we propose ModelTunnel v2 for efficient pre-training strategy search, and improve existing post-training methods by introducing chunk-wise rollout for load-balanced reinforcement learning and data-efficient tenary LLM, BitCPM. Regarding inference systems, we propose CPM.cu that integrates sparse attention, model quantization, and speculative sampling to achieve efficient prefilling and decoding. To meet diverse on-device requirements, MiniCPM4 is available in two versions, with 0.5B and 8B parameters, respectively. Sufficient evaluation results show that MiniCPM4 outperforms open-source models of similar size across multiple benchmarks, highlighting both its efficiency and effectiveness. Notably, MiniCPM4-8B demonstrates significant speed improvements over Qwen3-8B when processing long sequences. Through further adaptation, MiniCPM4 successfully powers diverse applications, including trustworthy survey generation and tool use with model context protocol, clearly showcasing its broad usability.

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While state-of-the-art speculative sampling methods use only a single layer and a language modeling (LM) head as the draft model to achieve impressive layer compression, their efficiency gains are substantially reduced for large-vocabulary LLMs, such as Llama-3-8B with a vocabulary of 128k tokens. To address this, we present FR-Spec, a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. By constraining the draft search to a frequency-prioritized token subset, our method reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. Experiments across multiple datasets demonstrate an average of 1.12$\times$ speedup over the state-of-the-art speculative sampling method EAGLE-2.