Bowen Qin

Xiang Li, Yiqun Yao, Xin Jiang et al. · tencent-ai, tsinghua

Large language models (LLMs) are considered important approaches towards foundational machine intelligence, achieving remarkable success in Natural Language Processing and multimodal tasks, among others. However, the carbon footprints and financial costs originating from heavy pre-training computation is a non-negligible issue. Progressive training methods, inspired by the neurogenesis process that grows neural structures, have shown potential to accelerate LLM pre-training. However, the algorithms, implementation, and practices for progressively training LLMs beyond 100B parameters remain underexplored. In this paper, we show that our model, namely FLM-101B, trained with our growth strategy under a budget of \$100K, reaches 80\% of the baselines' performances with only 10\% of their floating-point operations. We believe that further studies on progressive training will benefit the community by cutting down the costs and promoting green AI. The checkpoint of FLM-101B is released at https://huggingface.co/CofeAI/FLM-101B.

Jian Gao, Richeng Xuan, Zhaolu Kang et al.

The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian languages like Lao. To fill this gap, we introduce LaoBench, the first large-scale, high-quality, and multidimensional benchmark dataset dedicated to assessing LLMs' comprehensive language understanding and reasoning abilities in Lao. LaoBench comprises over 17,000 carefully curated samples spanning three core dimensions: knowledge application, K12 foundational education, and bilingual translation among Lao, Chinese, and English. The dataset is divided into open-source and closed-source subsets, with the closed-source portion enabling black-box evaluation on an official platform to ensure fairness and data security. Our data construction pipeline integrates expert human curation with automated agent-assisted verification, ensuring linguistic accuracy, cultural relevance, and educational value. Benchmarking multiple state-of-the-art LLMs on LaoBench reveals that current models still face significant challenges in mastering Lao across diverse tasks. We hope LaoBench will catalyze further research and development of AI technologies for underrepresented Southeast Asian languages.

Bowen Qin

CI failure logs are large (median 5k lines, max 200k in this corpus) and noisy. Coding agents that try to debug them depend on an upstream tool to reduce the log to a manageable context, but the field has had no public empirical comparison of which reductions preserve enough evidence for downstream LLM diagnosis. We introduce LogDx-CI, a benchmark that compares 11 context-reduction tools (raw, tail, grep, three RTK modes, two real LLM map-reduce summarizers, three hybrid routers) on 35 real GitHub Actions failure cases, scored by 3 LLM debugger families (Claude Haiku 4.5, Claude Sonnet 4.6, OpenAI gpt-5-mini) plus a Sonnet 4.6 tool-using agent. We report three load-bearing findings. (1)~Hybrid grep+tail routers dominate the cost-quality Pareto frontier; the top two methods score 0.670 / 0.666 at $\sim$ \$0.03 per case, same-ballpark quality as standalone grep at $4.5\times$ fewer tokens. (2)~In the agent-loop regime, the quality range across reduction tools collapses $7\times$ (single-shot spread 0.42 $\to$ agent-loop spread 0.059); the agent rescues weak contexts via follow-up tool calls. However, cost differences persist: weak contexts force the agent to issue 2--4$\times$ more tool calls to recover. (3)~A cross-family LLM-summary pair (gpt-5-mini summarizer feeding a Claude Haiku debugger) beats the same-family pair by $+0.071$ averaged across four diagnoser variants, falsifying the self-call-bias hypothesis on this task. The gpt-5-mini summarizer is also the agent-loop \#1 method (score 0.749) at $0.37$ tool-calls per case and $10\times$ lower reducer cost than the Haiku summarizer (\$0.18 vs \$1.75 per case). All data, code, per-case bundles, and reproducibility infrastructure are public.

Zheqi He, Yesheng Liu, Jing-shu Zheng et al.

We present FlagEvalMM, an open-source evaluation framework designed to comprehensively assess multimodal models across a diverse range of vision-language understanding and generation tasks, such as visual question answering, text-to-image/video generation, and image-text retrieval. We decouple model inference from evaluation through an independent evaluation service, thus enabling flexible resource allocation and seamless integration of new tasks and models. Moreover, FlagEvalMM utilizes advanced inference acceleration tools (e.g., vLLM, SGLang) and asynchronous data loading to significantly enhance evaluation efficiency. Extensive experiments show that FlagEvalMM offers accurate and efficient insights into model strengths and limitations, making it a valuable tool for advancing multimodal research. The framework is publicly accessible at https://github.com/flageval-baai/FlagEvalMM.

Siqi Fan, Bowen Qin, Peng Han et al.

Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems, wasting computation. Existing evaluations, based on token efficiency, give an incomplete view as they neglect problem difficulty and intermediate computation costs. We formalize reasoning efficiency as a relative measure between thinking and instruct models, treating instruct models as the minimal-effort baseline. A systematic study across four thinking models and multiple benchmarks reveals two consistent patterns: (i) instruct models achieve higher efficiency overall, and (ii) problem difficulty affects efficiency, with thinking models wasting computation on easy problems but providing value on harder ones. Building on this insight, we propose COTHINK, a simple two-stage pipeline: an instruct model drafts a brief outline, and a thinking model expands it. On GSM8K, MATH500, and AIME24, COTHINK cuts token usage by 21.1% while keeping accuracy on four thinking models, and remains competitive with strong efficiency baselines.

Bowen Qin, Duanyu Feng, Xi Yang

Reinforcement Learning from Human Feedback (RLHF) is a widely used framework for the training of language models. However, the process of using RLHF to develop a language model that is well-aligned presents challenges, especially when it comes to optimizing the reward model. Our research has found that existing reward models, when trained using the traditional ranking objective based on human preference data, often struggle to effectively distinguish between responses that are more or less favorable in real-world scenarios. To bridge this gap, our study introduces a novel method to estimate the preference differences without the need for detailed, exhaustive labels from human annotators. Our experimental results provide empirical evidence that incorporating margin values into the training process significantly improves the effectiveness of reward models. This comparative analysis not only demonstrates the superiority of our approach in terms of reward prediction accuracy but also highlights its effectiveness in practical applications.

Bowen Qin, Chen Yue, Fang Yin et al.

We conduct a moderate-scale contamination-free (to some extent) evaluation of current large reasoning models (LRMs) with some preliminary findings. We also release ROME, our evaluation benchmark for vision language models intended to test reasoning from visual clues. We attach links to the benchmark, evaluation data, and other updates on this website: https://flageval-baai.github.io/LRM-Eval/

Yesheng Liu, Hao Li, Haiyu Xu et al.

Multiple-choice question answering (MCQA) has been a popular format for evaluating and reinforcement fine-tuning (RFT) of modern multimodal language models. Its constrained output format allows for simplified, deterministic automatic verification. However, we find that the options may leak exploitable signals, which makes the accuracy metrics unreliable for indicating real capabilities and encourages explicit or implicit answer guessing behaviors during RFT. We propose ReVeL (Rewrite and Verify by LLM), a framework that rewrites multiple-choice questions into open-form questions while keeping answers verifiable whenever possible. The framework categorizes questions according to different answer types, apply different rewriting and verification schemes, respectively. When applied for RFT, we converted 20k MCQA examples and use GRPO to finetune Qwen2.5-VL models. Models trained on ReVeL-OpenQA match MCQA accuracy on multiple-choice benchmarks and improve OpenQA accuracy by about six percentage points, indicating better data efficiency and more robust reward signals than MCQA-based training. When used for evaluation, ReVeL also reveals up to 20 percentage points of score inflation in MCQA benchmarks (relative to OpenQA), improves judging accuracy, and reduces both cost and latency. We will release code and data publicly.

Duanyu Feng, Bowen Qin, Chen Huang et al.

The success of the reward model in distinguishing between responses with subtle safety differences depends critically on the high-quality preference dataset, which should capture the fine-grained nuances of harmful and harmless responses. This motivates the need to develop a dataset involving preference margins, which accurately quantify how harmless one response is compared to another. In this paper, we take the first step to propose an effective and cost-efficient framework to promote the margin-enhanced preference dataset development. Our framework, Legend, Leverages representation engineering to annotate preference datasets. It constructs the specific direction within the LLM's embedding space that represents safety. By leveraging this safety direction, Legend can then leverage the semantic distances of paired responses along this direction to annotate margins automatically. We experimentally demonstrate our effectiveness in both reward modeling and harmless alignment for LLMs. Legend also stands out for its efficiency, requiring only the inference time rather than additional training. This efficiency allows for easier implementation and scalability, making Legend particularly valuable for practical applications in aligning LLMs with safe conversations.