论文检索

Applications · Language, Speech and Dialog

Karthik Somayaji NS, Yuxuan Yin, Peng Li

In critical domains like clinical reporting, legal analysis, and policy drafting, large language models (LLMs) are increasingly expected to produce extended, fact‑rich narratives rather than isolated sentences. Reliable uncertainty quantification in such long‑form outputs is crucial. Existing techniques either assign a single confidence score to an entire paragraph or evaluate factual consistency by comparing extracted atomic facts across multiple generations. Some recent approaches represent fact–paragraph relationships using bipartite entailment graphs and derive uncertainty from fact centrality. However, these methods ignore the explicit dependencies among facts within a paragraph and the structural and semantic variation across multiple LLM outputs for the same prompt, missing a key source of uncertainty specific to long‑form generation. We propose **GAUSS** (**G**raph‑**A**ssisted **U**ncertainty **Q**uantification using **S**tructure and **S**emantics), a principled framework that models each generated paragraph as a semantic graph of atomic facts and their relations. We posit that uncertainty arises from structural and semantic discrepancies among these graphs across different samples. **GAUSS** quantifies uncertainty as the expected alignment cost between the semantic graph of an anchor paragraph and those of alternative generations. By capturing both semantic content and structural coherence, **GAUSS** offers a more interpretable and theoretically grounded measure of uncertainty than coarse, sentence‑level scores.

Applications · Language, Speech and Dialog

Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang, Jiajun Fan, Heng Wang, Siru Ouyang, Ming Zhong, Yizhu Jiao, Chengsong Huang, Xueqiang Xu 等

Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-$K$ results. A key reason is that retrievers and rerankers optimize solely for relevance, often selecting either trivial, answer-revealing passages or evidence that lacks the critical information required to answer the question, without considering whether the evidence is suitable for the generator. We propose \texttt{BAR-RAG}, which reframes the reranker as a boundary-aware evidence selector that targets the generator’s Goldilocks Zone—evidence that is neither trivially easy nor fundamentally unanswerable for the generator, but is challenging yet sufficient for inference and thus provides the strongest learning signal. \texttt{BAR-RAG} trains the selector with reinforcement learning using generator feedback, and adopts a two-stage pipeline that fine-tunes the generator under the induced evidence distribution to mitigate the distribution mismatch between training and inference. Experiments on knowledge-intensive question answering benchmarks show that \texttt{BAR-RAG} consistently improves end-to-end performance under noisy retrieval, achieving an average gain of 10.3\% over strong RAG and reranking baselines while substantially improving robustness.

Applications · Language, Speech and Dialog

Chen Xie, Yuling Shi, Xiaodong Gu, Beijun Shen

Code complexity metrics such as cyclomatic complexity have long been used to assess software quality and maintainability. With the rapid advancement of large language models (LLMs) on code understanding and generation tasks, an important yet underexplored question arises: do these traditional complexity metrics meaningfully characterize the difficulty LLMs experience when processing code? In this work, we empirically demonstrate that, after controlling for code length, classical metrics exhibit no consistent correlation with LLM performance, revealing a fundamental mismatch with model-perceived difficulty. To address this gap, we propose LM-CC, a novel code complexity metric designed from the perspective of LLMs. The core premise of LM-CC is that LLM-perceived difficulty is driven by the nonlinearity of program semantics. Accordingly, we decompose programs into semantic units based on entropy, organize these units into a compositional hierarchy, and quantify complexity as a principled aggregation of compositional level and branching-induced divergence, capturing cumulative model uncertainty during code processing. Our extensive experiments show that LM-CC not only correlates more strongly with LLM performance than traditional metrics but also that lowering it directly enhances task performance. The source code is available at: https://anonymous.4open.science/r/lm-cc-7EE6.

Applications · Language, Speech and Dialog

Ke Xue, Rongfei Fan, Kai Li, Shanping Yu, Puning Zhao, Jianping An

Diffusion models have recently set new benchmarks in Speech Enhancement (SE). However, most existing score-based models treat speech spectrograms merely as generic 2D images, applying uniform processing that ignores the intrinsic structural sparsity of audio, which results in inefficient spectral representation and prohibitive computational complexity. To bridge this gap, we propose **DVPD**, an extremely lightweight **D**ual-**V**iew **P**redictive **D**iffusion model, which uniquely exploits the dual nature of spectrograms as both visual textures and physical frequency-domain representations across both training and inference stages. Specifically, during training, we optimize spectral utilization via the Frequency-Adaptive Non-uniform Compression (FANC) encoder, which preserves critical low-frequency harmonics while pruning high-frequency redundancies. Simultaneously, we introduce a Lightweight Image-based Spectro-Awareness (LISA) module to capture features from a visual perspective with minimal overhead. During inference, we propose a Training-free Lossless Boost (TLB) strategy that leverages the same dual-view priors to refine generation quality without any additional fine-tuning. Extensive experiments across various benchmarks demonstrate that DVPD achieves state-of-the-art performance while requiring only **35** of the parameters and **40%** of the inference MACs compared to SOTA lightweight model, PGUSE. These results highlight DVPD's superior ability to balance high-fidelity speech quality with extreme architectural efficiency. Code and audio samples are available at the anonymous website: https://anonymous.4open.science/r/dvpd_demo-E630

Applications · Language, Speech and Dialog

Linhao Luo, Zicheng Zhao, Junnan Liu, Zhangchi Qiu, Junnan Dong, Serge Panev, Chen Gong, Thuy-Trang Vu, Gholamreza Haffari, Dinh Phung 等

Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge. Retrieval-augmented generation (RAG) mitigates this by incorporating external knowledge, yet existing RAGs struggle with knowledge-intensive tasks due to fragmented information and weak modeling of knowledge structure. Graphs offer a natural way to model relationships within knowledge, but LLMs are inherently unstructured and cannot effectively reason over graph-structured data. Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them. However, these methods often depend on ad-hoc graph designs, heuristic search, or costly agent pipelines, which hinder scalability and generalization. To address these challenges, we present G-reasoner, a unified framework that integrates graph and language foundation models for scalable reasoning over diverse graph-structured knowledge. Central to our approach is QuadGraph, a standardized four-layer abstraction that unifies heterogeneous knowledge sources into a common graph representation. Building on this, we introduce a 34M-parameter graph foundation model (GFM) that jointly captures graph topology and textual semantics, and is integrated with LLMs to enhance reasoning in downstream applications. To ensure scalability and efficiency, mixed-precision training and distributed message-passing are implemented to scale GFM with more GPUs. Extensive experiments on six benchmarks show that G-reasoner consistently outperforms state-of-the-art baselines, significantly enhances LLM reasoning, and achieves strong efficiency and cross-graph generalization.

Applications · Language, Speech and Dialog

Kai Zhang, Xinyuan Zhang, Ejaz Ahmed, Hongda Jiang, Caleb Kumar, Kai Sun, Zhaojiang Lin, Sanat Sharma, Shereen Oraby, AARON COLAK 等

Accurate recall from large-scale memories remains a core challenge for memory-augmented AI assistants performing question answering (QA), especially in similarity-dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance-aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals—relevance, importance, and temporal alignment—using an adaptive mutual information (MI)-driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms state-of-the-art baselines, verifying its superiority in context-aware memory recall.

Applications · Language, Speech and Dialog

Yefan Zhou, Austin Xu, Yilun Zhou, Janvijay Singh, Jiang Gui, Shafiq Joty

Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems across diverse domains. One effective paradigm for test-time scaling (TTS) involves LLM generators producing multiple solution candidates, with LLM verifiers assessing the correctness of these candidates without reference answers. In this paper, we study generative verifiers, which perform verification by generating chain-of-thought (CoT) reasoning followed by a binary verdict. We systematically analyze verification dynamics across three dimensions -- problem difficulty, generator capability, and verifier generation capability -- through empirical studies on 12 benchmarks across mathematical reasoning, knowledge, and natural language reasoning tasks using 14 open-source models (2B to 72B parameter range) and GPT-4o. Our experiments reveal three key findings about verification effectiveness: (1) Easy problems allow verifiers to more reliably certify correct responses; (2) Weak generators produce errors that are easier to detect than strong generators; (3) Verification ability is generally correlated with the verifier's own problem-solving capability, but this relationship varies with problem difficulty. These findings reveal opportunities for optimizing basic verification strategies in TTS applications. First, given the same verifier, some weak generators can nearly match stronger ones in post-verification TTS performance (e.g., the Gemma2-9B to Gemma2-27B performance gap shrinks by 75.7%). Second, we identify cases where strong verifiers offer limited advantages over weak ones, as both fail to provide meaningful verification gains, suggesting that verifier scaling alone cannot overcome fundamental verification challenges.

Applications · Language, Speech and Dialog

Silong Dai, Changzhi Sun, Haolun Wu, Huanran Zheng, Tao Ji, Junchi Yan, Yuanbin Wu, Dell Zhang, Xiaoling Wang, Xuelong Li

Recent advancements in reinforcement learning from verifiable rewards (RLVR), particularly through Group Relative Policy Optimization (GRPO), have significantly improved the capabilities of large language models (LLMs) for interactive coding agents. However, these methods overlook process-verifiable environment feedback (e.g., code execution failures), leading to inaccurate advantage estimation at each reasoning step and insufficient learning. To address this issue, we propose Group Verification-based Policy Optimization (GVPO), a novel RL algorithm that introduces an advantage shaping framework integrating both outcome-verifiable and process-verifiable signals. While outcome-verifiable rewards ensure alignment with long-term task objectives, process-verifiable feedback derived from intermediate execution traces (e.g., syntax errors, runtime exceptions) serves as corrective shaping terms at the step level. By jointly leveraging these two forms of verifiability, GVPO achieves more accurate credit assignment, balancing short-term process guidance with long-term outcome alignment. This unified formulation yields more stable optimization, faster convergence, and stronger generalization in complex interactive environments. A 32B-parameter agent trained with GVPO in the AppWorld environment outperforms OpenAI’s o1 agent by 12.7\% on the more challenging Test-C split and surpasses the strongest 32B RL-trained state-of-the-art baseline by 3.7\%.

Applications · Language, Speech and Dialog

Haipeng Luo, Huawen Feng, Qingfeng Sun, Can Xu, Kai Zheng, Yufei Wang, TAO YANG, Winston Hu, Yansong Tang

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations. In this work, we present AgentMath, an agent framework that seamlessly integrates language models' reasoning capabilities with code interpreters' computational precision to efficiently tackle complex mathematical problems. Our approach introduces three key innovations: (1) An automated method that converts natural language chain-of-thought into structured tool-augmented trajectories, generating high-quality supervised fine-tuning (SFT) data to alleviate data scarcity; (2) A novel agentic reinforcement learning (RL) paradigm that dynamically interleaves natural language generation with real-time code execution. This enables models to autonomously learn optimal tool-use strategies through multi-round interactive feedback, while fostering emergent capabilities in code refinement and error correction; (3) An efficient training system incorporating innovative techniques, including request-level asynchronous rollout scheduling, agentic partial rollout, and prefix-aware weighted load balancing, achieving 4-5× speedup and making efficient RL training feasible on ultra-long sequences with scenarios with massive tool calls. Extensive evaluations show that AgentMath achieves state-of-the-art performance on challenging mathematical competition benchmarks including AIME24, AIME25, and HMMT25, substantially outperforming frontier open‑source models of comparable size. Specifically, AgentMath-30B-A3B attains 90.6\%, 86.4\%, and 73.8\% accuracy respectively, surpassing OpenAI-o3-mini and Claude-Opus-4.0-Thinking while remaining competitive with OpenAI-o3, Gemini-2.5-Pro, and DeepSeek-R1-671B-0528. These results validate the effectiveness of our approach and pave the way for building scalable mathematical reasoning agents.

Applications · Language, Speech and Dialog

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Caswell, Alex Pentland, Sercan Arik, Chen-Yu Lee, Sayna Ebrahimi

Scaling laws research has focused overwhelmingly on English—yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model parameters, 400+ training languages and 48 evaluation languages. We introduce the Adaptive Transfer Scaling Law (ATLAS) for both monolingual and multilingual pretraining, which outperforms existing scaling laws' out-of-sample generalization often by more than $0.3$ $R^2$. Our analyses of the experiments shed light on multilingual learning dynamics, transfer properties between languages, and the curse of multilinguality. First, we derive a cross-lingual transfer matrix, empirically measuring mutual benefit scores between $38 \times 38=1444$ language pairs. Second, we derive a language-agnostic scaling law that reveals how to optimally scale model size and data when adding languages without sacrificing performance. Third, we identify the computational crossover points for when to pretrain from scratch versus finetune from multilingual checkpoints. We hope these findings provide the scientific foundation for democratizing scaling laws across languages, and enable practitioners to efficiently scale models—beyond English-first AI.

Applications · Language, Speech and Dialog

Shangbin Feng, Wenhao Yu, Yike Wang, Hongming Zhang, Yulia Tsvetkov, Dong Yu

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best of both worlds through model collaboration, where different models in the training pipeline collaborate and complement each other. Since LM responses feature interleaving skills that favor different models, we propose Switch Generation, where pretrained and aligned model versions take turns to ``speak'' in a response sequence. Specifically, we train a switcher LM by learning from outcomes of choosing different models to generate the next segment across diverse queries and contexts. At inference time, the switcher LM guides different model checkpoints to dynamically generate the next segment where their strengths are most needed. Extensive experiments with 8 model collaboration baselines and 18 datasets show that 1) model collaboration consistently outperforms individual models on 16 out of 18 tasks, and 2) Switch Generation further outperforms baselines by 12.9% on average. Further analysis reveals that Switch Generation discovers compositional skills to solve problems where individual models struggle and generalizes to unseen models and tasks, reusing and repurposing by-products in expensive model training pipelines that are otherwise discarded.

Applications · Language, Speech and Dialog

Xuemiao Zhang, Can Ren, Chengying Tu, Rongxiang Weng, Shuo Wang, Hongfei Yan, Jingang Wang, Xunliang Cai

Recent progress in large reasoning models for challenging mathematical reasoning has been driven by reinforcement learning (RL). Incorporating long chain-of-thought (CoT) data during mid-training has also been shown to substantially improve reasoning depth. However, current approaches often utilize CoT data indiscriminately, leaving open the critical question of which data types most effectively enhance model reasoning capabilities. In this paper, we define the foundation model's reasoning potential for the first time as the inverse of the number of independent attempts required to correctly answer the question, which is strongly correlated with the final model performance. We then propose utilizing diverse data enriched with high-value reasoning patterns to expand the reasoning potential. Specifically, we abstract atomic reasoning patterns from CoT sequences, characterized by commonality and inductive capabilities, and use them to construct a core reference set enriched with valuable reasoning patterns. Furthermore, we propose a dual-granularity algorithm involving chains of reasoning patterns and token entropy, efficiently selecting high-value CoT data (CoTP) from the data pool that aligns with the core set, thereby training models to master reasoning effectively. Only 10B-token CoTP data enables the 85A6B Mixture-of-Experts (MoE) model to improve by **9.58\%** on the challenging AIME 2024 and 2025, and to raise the upper bound of downstream RL performance by **7.81\%**.

Applications · Language, Speech and Dialog

Qianben Chen, Jingyi Cao, Jiayu Zhang, Tianrui Qin, LiXiaowan, Zhu, Dingfeng Shi, He Zhu, Minghao Liu, Xiaobo Liang 等

Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but often lag in deep reasoning. This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries, where both families tend to overthink or over-call tools. In this work, we present Adaptive Agent Foundation Model (A$^2$FM), a unified framework that follows a route-then-align principle: the model first learns task-aware routing and then aligns mode-specific trajectories under a shared backbone. To address the inefficiency gap, we introduce a third instant mode that handles simple queries directly, preventing unnecessary reasoning or tool calls while complementing the agentic and reasoning modes. To jointly enhance accuracy and efficiency, we propose Adaptive Policy Optimization (APO), which enforces adaptive sampling across modes and applies a cost-regularized reward. On the 32B scale, A$^2$FM achieves 13.4\% on BrowseComp, 70.4\% on AIME25, and 16.7\% on HLE, setting new SOTA among comparable models and performing competitively with frontier LLMs across agentic, reasoning, and general benchmarks. Notably, the adaptive execution achieves a cost of pass of only \$0.00487 per correct answer—cutting cost by 45.2\% relative to reasoning and 33.5\% relative to agentic, thus delivering substantially higher cost efficiency while maintaining comparable accuracy.

Applications · Language, Speech and Dialog

Yonggang Zhang, Jianqi Gao, Jie Lu

Large language models (LLMs) have demonstrated remarkable success across diverse domains through in-context learning or fine-tuning. However, adapting LLMs to Knowledge Base Question Answering (KBQA) remains challenging, as KBQA necessitates multi-step reasoning over large-scale structured knowledge bases. Directly prompting LLMs with entire knowledge bases incurs prohibitive computational costs, while existing methods provide limited guidance on effectively fine-tuning LLMs for such complex reasoning tasks. In this work, we propose Chain-of-Decomposition (\texttt{CoD}), a novel framework that decomposes KBQA into three modular steps: (1) an LLM-free retrieval module to extract query-relevant subgraphs from the knowledge base, (2) a parameter-free reformulation step that transforms retrieved contexts into structured reasoning paths, and (3) a lightweight LLM-based reasoning module trained to evaluate the logical validity of each path. By isolating computation-heavy retrieval and rule-based reformulation from LLM reasoning, \texttt{CoD} reduces task complexity and enables efficient fine-tuning focused solely on the final verification step. Comprehensive experiments demonstrate that Llama-2 7B, fine-tuned with the proposed \texttt{CoD} surpasses strong baselines, including GPT-4 augmented with retrieved knowledge, achieving state-of-the-art performance on WebQSP and CWQ benchmarks. Our code is publicly available at \url{https://github.com/YonggangZhang9412/KBQA-CoD}.

Applications · Language, Speech and Dialog

Cheng-Han Chiang, Xiaofei Wang, Linjie Li, Chung-Ching Lin, Kevin Lin, Shujie LIU, Zhendong Wang, Zhengyuan Yang, Hung-yi Lee, Lijuan Wang

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking process before responding. In contrast, humans typically engage in complex mental reasoning internally, enabling them to communicate ideas clearly and concisely. Thus, integrating an unspoken thought process into SLMs is highly desirable. While naively generating a complete chain-of-thought (CoT) reasoning before starting to talk can enable thinking for SLMs, this induces additional latency for the speech response, as the CoT reasoning can be arbitrarily long. To solve this issue, we propose STITCH, a novel generation method that alternates between the generation of unspoken reasoning chunks and spoken response chunks. Since the audio duration of a chunk of spoken response is much longer than the time to generate the tokens in a chunk of spoken response, we use the remaining free time to generate the unspoken reasoning tokens. When a chunk of audio is played to the user, the model continues to generate the next unspoken reasoning chunk, achieving simultaneous thinking and talking. Remarkably, STITCH matches the latency of baselines that cannot generate unspoken CoT by design while outperforming those baselines by 15% on math reasoning datasets; STITCH also performs equally well on non-reasoning datasets as those baseline models. Some animations and demonstrations are on the project page: https://d223302.github.io/STITCH.

Applications · Language, Speech and Dialog

Tianshu Zhang, Huan Sun

Autonomous science agents, built on large language models (LLMs), are increasingly being investigated to generate hypotheses, design experiments, and produce reports. Prior science agents primarily focus on open-ended scientific problems, where such outputs—hypotheses, experiments, or analyses are inherently subjective and thus difficult to evaluate rigorously. In contrast, existing scientific coding benchmarks provide tasks with clearly defined, executable outputs that enable objective assessment. However, current agent-based approaches to these benchmarks remain engineering-driven pipelines, lacking principled framework design. This mismatch exposes a gap: the absence of end-to-end, principled science agent frameworks for scientific coding tasks. We address this gap by focusing on scientific coding tasks, where evaluation can be made rigorously, and introducing an agent framework SciNav (Scientific Navigator) that enables more effective solution exploration. Our framework is designed to operate efficiently under constrained search budgets, moving beyond reliance on pre-defined success metrics and prolonged search cycles. Inspired by findings that comparative judgments often reveal finer-grained quality differences and therefore provide greater discriminative power than absolute scoring, our framework leverages pairwise relative judgments within a tree search process to select top-K promising solution branches, prune low-potential ones, and progressively narrow down the solution candidates on the selected branches guided by relative comparisons. We demonstrate our agent's effectiveness across different types of tasks on two benchmarks. Experiments show that SciNav significantly outperforms direct prompting and prior agents like OpenHands and Self-Debug across different base models, task types, and difficulty levels, and exceeds different frontier comparators such as random selection and LLM absolute scoring. These results confirm the strength of our agent design and highlight the effectiveness of relative judgment–guided top-K search for high-quality scientific coding, marking a step toward more practical science agents.

Applications · Language, Speech and Dialog

Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. Starting from a single base LLM, R-Zero initializes two independent models with distinct roles, a Challenger and a Solver. These models are optimized separately and co-evolve through interaction: the Challenger is rewarded for proposing tasks near the edge of the Solver capability, and the Solver is rewarded for solving increasingly challenging tasks posed by the Challenger. This process yields a targeted, self-improving curriculum without any pre-existing tasks and labels. Empirically, R-Zero substantially improves reasoning capability across different backbone LLMs, e.g., boosting the Qwen3-4B-Base by +6.49 on math-reasoning benchmarks and +7.54 on general-domain reasoning benchmarks.

Applications · Language, Speech and Dialog

Zican Hu, Shilin Zhang, Yafu Li, Jianhao (Elliott) Yan, Xuyang Hu, Leyang Cui, Xiaoye Qu, Chunlin Chen, Yu Cheng, Zhi Wang

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models (LLMs). Due to vast state-action spaces and reward sparsity in reasoning tasks, existing methods often struggle with deficient exploration and poor sample efficiency. In the paper, we propose **DIVER** (**D**iversity-**I**ncentivized Exploration for **V**ersatil**E** **R**easoning), an innovative framework that highlights the pivotal role of global sequence-level diversity to incentivize deep exploration for versatile reasoning. We first conduct a primary empirical study to reveal a strong positive correlation between global diversity and reasoning capacity. Building on this insight, we introduce global diversity incentives as an intrinsic reward to promote deep exploration in a semantically structured space. Incorporating the intrinsic reward, we develop a potential-based reward shaping mechanism to preserve optimal policy invariance and design simple heuristics to mitigate possible reward hacking. Experimental results show that DIVER outperforms competitive RLVR baselines with various exploration strategies on both in-domain and out-of-domain tasks, excelling in both Pass@1 and Pass@k evaluations. Our code is available at https://github.com/NJU-RL/DIVER.

Applications · Language, Speech and Dialog

David Samuel, Lucas Charpentier

This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular approach, partly because of its training efficiency; however, that comes at the cost of sensitivity to overfitting. On the other hand, masked-diffusion models are less efficient to train while being more resilient to overfitting. In this work, we demonstrate that dual-objective training achieves the best of both worlds. To derive the optimal balance between both objectives, we train and evaluate 50 language models under varying levels of data repetition. We show that it is optimal to combine both objectives under all evaluated settings and that the optimal balance is similar whether targeting autoregressive or masked-diffusion downstream performance.

Applications · Language, Speech and Dialog

Tiannuo Yang, Zebin Yao, Bowen Jin, Lixiao Cui, Yusen Li, Gang Wang, Xiaoguang Liu, Willie Neiswanger

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval-induced stalls, which lead to cascading latency—where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce SearchAgent-X, a high-efficiency inference framework for LLM-based search agents. SearchAgent-X leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that SearchAgent-X consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4× higher throughput and 5× lower latency, without compromising generation quality. Code is available at https://github.com/tiannuo-yang/SearchAgent-X.