Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising framework for optimizing large language models in reasoning tasks. However, existing RLVR algorithms focus on different granularities, and each has complementary strengths and limitations. Group Relative Policy Optimization (GRPO) updates the policy with token-level importance ratios, which preserves fine-grained credit assignment but often suffers from high variance and instability. In contrast, Group Sequence Policy Optimization (GSPO) applies single sequence-level importance ratios across all tokens in a response that better matches sequence-level rewards, but sacrifices token-wise credit assignment. In this paper, we propose Dynamic Hybrid Policy Optimization (DHPO) to bridge GRPO and GSPO within a single clipped surrogate objective. DHPO combines token-level and sequence-level importance ratios using weighting mechanisms. We explore two variants of the mixing mechanism, including an averaged mixing and an entropy-guided mixing. To further stabilize training, we employ a branch-specific clipping strategy that constrains token-level and sequence-level ratios within separate trust regions before mixing, preventing outliers in either branch from dominating the update. Across seven challenging mathematical reasoning benchmarks, experiments on both dense and MoE models from the Qwen3 series show that DHPO consistently outperforms GRPO and GSPO. Our code is publicly available at https://github.com/XMUDeepLIT/DHPO.
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
Large Language Models have shown strong performance in Machine Translation, yet they often suffer from paraphrasing errors, omissions, or hallucinations when the input contains translation-specific elements (e.g., URLs, slang, and idioms) that require strict preservation or controlled transformation, undermining the reliability of critical details.We propose CEMT, a Controllable Element-Oriented Machine Translation framework inspired by the analysis–strategy–generation paradigm in human translation. CEMT first employs an Element Detection Module to identify translation-specific elements, and then introduces a Translation Module that decomposes the translation process into linguistically grounded analysis, strategy formulation, and final generation, thereby guiding the reliable translation of these elements. We further introduce a CoT Judge model during training that provides step-wise supervision over the accuracy and consistency of the translation process.On the WMT23/24 Chinese–English benchmarks, CEMT improves performance over existing Machine Translation models while significantly reducing element-level constraint violations.
Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets and 33 models. Moreover, it provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing, and integrates 10 representative routing baselines. Using LLMRouterBench, we systematically re-evaluate the field. While confirming strong model complementarity—the central premise of LLM routing—we find that many routing methods exhibit similar performance under unified evaluation, and several recent approaches, including commercial routers, fail to reliably outperform a simple baseline. Meanwhile, a substantial gap remains to the Oracle, driven primarily by persistent model-recall failures. We further show that backbone embedding models have limited impact, that larger ensembles exhibit diminishing returns compared to careful model curation, and that the benchmark also enables latency-aware analysis. All code and data are available at https://github.com/ynulihao/LLMRouterBench.
High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds on closed tasks, yet the humanities and social sciences (HSS) are overlooked, and their open-ended nature makes synthesis challenging.Moving beyond prior capability-centric, fragmented attempts, we adopt a subject-centric paradigm, define the first HSS domain system covering 14 mainstream fields, and introduce HSS-Synth—the first data synthesis pipeline for HSS.HSS-Synth comprises: (1) constructing seed document from web corpora via multi-step filtering and text refinement evaluated by a judge; (2) specifying “requirements + persona” to backtranslate seed document into diverse yet faithful instructions with strict Q&A alignment check; and (3) breaking LLM response limits via teacher-forced Answering that fed seed documents during response to anchor semantics, reduce hallucinations, and preserve tone and integrity.HSS-Synth yields 237k high-quality, diverse instruction-tuning samples that outperform 14 leading baselines on 16 benchmarks. The fine-tuned Qwen3-8B-Base set new SOTA and approached official Qwen3-8B, improving both human preference and knowledge capability without performance seesaws. Extensive experiments demonstrate the HSS-Synth’s robustness and transferability.Our code is publicly available at https://github.com/pengr/HSS-Synth.
Transcending the single-preference paradigm, aligning LLMs with diverse human values is pivotal for robust deployment. Contemporary Multi-Objective Preference Alignment (MPA) approaches predominantly rely on static linear scalarization or rigid gradient projection to navigate these trade-offs. However, by enforcing strict conflict avoidance or simultaneous descent, these paradigms often prematurely converge to local stationary points. While mathematically stable, these points represent a conservative compromise where the model sacrifices potential global Pareto improvements to avoid transient local trade-offs. To break this deadlock, we propose Pareto-Lenient Consensus (PLC), a game-theoretic framework that reimagines alignment as a dynamic negotiation process. Unlike rigid approaches, PLC introduces consensus-driven lenient gradient rectification, which dynamically tolerates local degradation provided there is a sufficient dominant coalition surplus, thereby empowering the optimization trajectory to escape local suboptimal equilibrium and explore the distal Pareto-optimal frontier. Theoretical analysis validates PLC can facilitate stalemate escape and asymptotically converge to a Pareto consensus equilibrium. Moreover, extensive experiments show that PLC surpasses baselines in both fixed-preference alignment and global Pareto frontier quality. This work highlights the potential of negotiation-driven alignment as a promising avenue for MPA. Our codes are available at https://anonymous.4open.science/r/aaa-6BB8.
Adapting large language models (LLMs) to domain-specific tasks via fine-tuning is often infeasible: models are protected by intellectual property, while sensitive data cannot be shared due to privacy regulations. A promising paradigm, Offsite Tuning (OT), addresses this challenge by constructing an emulator of the original model. Data owners leverage the emulator to train an adapter on downstream data, which is then plugged back into the original model, enabling knowledge transfer without transmitting either the original model or the raw data. However, emulators constructed by existing OT-based methods often retain substantial inference capabilities, thereby exposing model capability privacy and posing risks of misuse. To address this, we propose Loss Landscape Elevation Offsite Tuning (LLEOT), a framework that secures data privacy as well as model parameter and capability privacy. At its core, Loss Landscape Elevation (LLE) enforces a fixed margin between the loss landscapes of the emulator and the original model. We theoretically demonstrate that LLE simultaneously (i) degrades emulator inference via perplexity amplification and (ii) preserves gradient alignment, ensuring consistent convergence for adapter training. Extensive experiments confirm that LLEOT achieves strong adaptation performance while effectively mitigating emulator misuse. Code is available at https://github.com/Z-eloto/LLEOT.
The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide accurate natural language answers to knowledge-seeking questions during software development. To investigate the importance of Dev Knowledge QA in AI-assisted software development and the extent to which it has been explored, we conduct a preliminary analysis of real user–LLM dialogues from WildChat. Our findings indicate that Dev Knowledge QA plays a significant role in real-world software development scenarios, and these raw dialogues cannot be directly used to construct a Dev Knowledge QA benchmark. Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries. To bridge this gap, we design a three-phase pipeline that transforms real-world dialogue into simple development knowledge-seeking QA pairs. Through this pipeline, we introduce SimpleDevQA, a multilingual Dev Knowledge QA benchmark inspired by real user dialogues. This dataset covers three languages (English, Chinese, and Russian), and focuses on questions with unique, short, and verifiable answers, making evaluation more accurate and simple. Extensive experiments with 18 mainstream LLMs show that closed-source models generally perform best on SimpleDevQA. We also find that RAG-based knowledge injection improves accuracy, and that Dev Knowledge QA performance correlates with both model confidence and code-generation capability. To facilitate the replication study, we have released our data and code at: https://github.com/DeepSoftwareAnalytics/SimpleDevQA.
HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST
PDF ↗Zero-shot Dialog State Tracking (zs-DST) is essential for enabling Task-Oriented Dialog Systems (TODs) to generalize to new domains without costly data annotation. A central challenge lies in the semantic misalignment between dynamic dialog contexts and static prompts, leading to inflexible cross-layer coordination, domain interference, and catastrophic forgetting. To tackle this, we propose Hierarchical Collaborative Low-Rank Adaptation (HiCoLoRA), a framework that enhances zero-shot slot inference through robust prompt alignment. It features a hierarchical LoRA architecture for dynamic layer-specific processing (combining lower-layer heuristic grouping and higher-layer full interaction), integrates Spectral Joint Domain-Slot Clustering to identify transferable associations (feeding an Adaptive Linear Fusion Mechanism), and employs Semantic-Enhanced SVD Initialization (SemSVD-Init) to preserve pre-trained knowledge. Experiments on multi-domain datasets MultiWOZ and SGD show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST.
Enrich, Aggregate, and Generate: Three-stage Biomedical Data-to-Text Generation Using Large Language Models in Low-resource Scenarios
PDF ↗Biomedical data-to-text generation aims at generating textual natural language descriptions that can fluently and precisely describe the biomedical structured data. However, biomedical data-to-text generation faces the dilemma of a lack of labeled data due to the privacy and scarcity of medical data. Large language models (LLMs) have demonstrated the ability to solve few-shot tasks through in-context learning (ICL). In this paper, we are the first to explore the performance of different LLMs in the biomedical data-to-text generation task.To address the issues of semantic sparsity and misinterpretation of numerical values in biomedical structured data, we propose an EAG (Enrich, Aggregate, and Generate) framework, a simple but efficient LLM-based three-stage biomedical D2T approach in low-resource scenarios. We conduct extensive evaluations of closed-source general LLMs, open-source general LLMs, and open-source medical LLMs. The results show that the EAG framework provides good interpretability and superior performance, achieving state-of-the-art performance on the BioLeaflets dataset. The code and data will be released at https://github.com/FXLP/EAG.
While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with structural fractures. To this end, we introduce PLOTTER, a framework that performs narrative planning on structural graph representations instead of direct sequential text representations in existing work. Specifically, PLOTTER executes the Evaluate-Plan-Revise cycle on the event graph and character graph. By diagnosing and repairing issues of the graph topology under rigorous logical constraints, the model optimizes the causality and narrative skeleton before complete context generation. Experiments demonstrate that PLOTTER significantly outperforms representative baselines across diverse narrative scenarios. These findings verify that manipulating narrative planning on structural graph representations—rather than direct text representations—is crucial to enhance the long-context reasoning of LLMs in complex narrative generation.
Large Language Models (LLMs) have achieved remarkable success in text summarization, particularly through the integration of reinforcement learning. However, maintaining logical coherence and contextual consistency remains a pervasive challenge in long-form generation, often hindering the production of high-quality, unified summaries. To address these persistent issues, we propose TRAC, a framework that introduces a token-level reward function by integrating relative sentence gain, inter-sentence attention, and a Gaussian length penalty. By training a Process Reward Model (PRM) to provide fine-grained, step-wise supervision, TRAC ensures superior structural integrity and fluency during the generation process. Experimental results demonstrate that TRAC outperforms the sequence-level baseline by 11.05% in Fluency and 10.61% in Relevance. Furthermore, it achieves significant gains over competitive baselines such as FIGA and TLCR, underscoring its effectiveness and generalizability in high-quality NLP summarization.
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
PDF ↗While Large Language Models (LLMs) have revolutionized code generation, standard “System 1” approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model’s weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-only training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B-14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, efficient reasoning and reflection patterns. The source code and data are available at https://github.com/juyongjiang/ReflexiCoder.
MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction
PDF ↗Reinforcement learning (RL) is widely applied to boost the performance of pretrained models, yet its training efficiency is severely constrained by rollout generation. While speculative decoding based on multi-token prediction (MTP) offers a potential acceleration pathway, its widespread adoption is hindered by the absence of MTP in vanilla pretrained models and the rapid degradation of the MTP acceptance length in RL training. To address these issues, this paper proposes MTP-RL, a two-stage framework that pioneers effective training of MTPs in RL and accelerates the rollout phase for diverse models. It involves a pipeline to equip the multi-layer parameter-sharing MTP for all models and an innovative advantage-aware MTP optimization strategy to facilitate policy-aligned training of MTPs. Experiments demonstrate that our method not only achieves stable growth of acceptance length during RL training, but also accelerates RL rollouts, achieving an average 23.1%–55.3% reduction in rollout time compared to baselines.
Memory serves as a pivotal component in interactive response generation, supplying essential background information and referential knowledge for dialogues. Conventional interactive algorithms have predominantly treated memory as a merely contextual element, largely neglecting the nuanced cognitive processes involved in individualized memory encoding and retrieval. This conceptual gap has led to the prevailing schema where memory-enhanced dialogue datasets incorporate monolithic, undifferentiated memory content, failing to capture the personalized nature of persoa memory processing. Grounded in the self-reference effect from cognitive psychology, we introduce a Multi-Turn Dialogue Dataset with Personalized Contextual Memory (), establishing a comprehensive benchmark to facilitate advanced research on personalized memory processing algorithms.
Despite the pivotal role of numerical reasoning as the cornerstone of mathematical capabilities in large language models (LLMs) across applications, few benchmarks evaluate LLMs by integrating numerical processing and mathematical reasoning, hindering the interpretability of failures in math tasks. We introduce PyraMathBench, a comprehensive hierarchical benchmark with 27,215 questions derived from 7,404 math word problems, spanning 4 key cognitive aspects, 14 subcategories, and 2 modalities. Experiments reveal that LLMs’ performance is severely compromised by inadequate numerical computation and weak handling of abstract numerical questions. To address this, we propose the Smart Optimization Learning-based VErsatile module (SOLVE) and Interactive Relative Policy Optimization (IRPO), which enhance LLMs’ numerical-mathematical synergy via efficient tool calls (fuzzy matching and low-quality call rejection). Comparative experiments show Qwen-2.5 achieves a 5.0 score improvement with SOLVE and IRPO training.
Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models
PDF ↗Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other’s logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method. Our code is available at [link](https://github.com/lakhfskn/anonymous-code-of-arr).
Distilling large reasoning models (LRMs) has become essential for making their Long-CoT reasoning capabilities practical, as full-scale inference remains computationally prohibitive. Existing curation-based approaches, which select complete reasoning traces post-hoc, overlook the collaborative potential of heterogeneous teachers and fail to adapt exploration dynamically, often leading to redundant sampling and missed opportunities for complementary reasoning. To address this, we introduce CoRD, a collaborative multi-teacher decoding framework that performs step-wise reasoning synthesis guided by predictive perplexity–based scoring and beam search. This approach enables heterogeneous LRMs to jointly construct coherent reasoning trajectories while maintaining diverse, high-potential hypotheses efficiently. Experiments show that CoRD generates higher-quality reasoning data and achieves student performance approaching teacher-level results, demonstrating that fine-grained collaboration among diverse LRMs yields structured, efficient, and robust reasoning distillation. The dataset and model are available at https://github.com/DISL-Lab/CoRD
Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gains. Controlling reasoning length without sacrificing performance is therefore important, but remains challenging, especially under tight thinking budgets. We propose budget guidance, a simple yet effective method for steering the reasoning process of LLMs toward a target budget without requiring any LLM fine-tuning. Our approach introduces a lightweight predictor that models a Gamma distribution over the remaining thinking length during next-token generation. This signal is then used to guide generation in a soft, token-level manner, ensuring that the overall reasoning trace adheres to the specified thinking budget. Budget guidance enables natural control of the thinking length, along with significant token efficiency improvements over baseline methods on challenging math benchmarks. For instance, it achieves up to a 26% accuracy gain on the MATH-500 benchmark under tight budgets compared to baseline methods, while maintaining competitive accuracy with only 63% of the thinking tokens used by the full-thinking model. Budget guidance also generalizes to broader task domains and exhibits emergent capabilities, such as estimating question difficulty. We release our code and model weights at https://github.com/UMass-Embodied-AGI/BudgetGuidance.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
PDF ↗Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise.Through an empirical study, we observe that responses with medium consistency form an ambiguity region and constitute the primary source of reward noise.Crucially, we find that such spurious signals can be even amplified through group-relative advantage estimation.Motivated by these findings, we propose a unified framework, Debiased and Denoised test-time Reinforcement Learning (DDRL), to mitigate spurious signals.Concretely, DDRL first applies a frequency-based sampling strategy to exclude ambiguous samples while maintaining a balanced set of positive and negative examples.It then adopts a debiased advantage estimation with fixed advantages, removing the bias introduced by group-relative policy optimization.Finally, DDRL incorporates a consensus-based off-policy refinement stage, which leverages the rejection-sampled dataset to enable efficient and stable model updates.Experiments on three large language models across multiple mathematical reasoning benchmarks demonstrate that DDRL consistently outperforms existing TTRL baselines.The code is available at https://github.com/yuyongcan/DDRL.
Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.