Yixiao Chen, Ke Cheng, Yue Liu, Jun Zhang, Jie Jiang
What should data teach a language model at a particular point in training? A circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B tokens. Availability counterfactuals then distinguish writing content from invoking available memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.
Kehan Zheng, Deyao Hong, Qian Li, Jun Zhang, Jie Jiang, Hongning Wang
Conventional recommender systems operate within platform-specific catalogs, limiting access to potentially valuable resources across platforms. We propose user-centered agentic recommendation, a paradigm in which user agents compare recommendations from competing platform agents, and formalize their interaction as a repeated game. Platforms strategically modify descriptions without changing intrinsic item value, while each user agent assesses platform credibility using feedback from consumed items only. Our analysis shows that expanded resource access need not improve user welfare: strategic misrepresentation and limited verification can offset the benefits of platform competition. We quantify when platform credibility assessment allows users to benefit from broader access despite strategic exaggeration. Our analysis identifies resource and reporting conditions that guarantee higher average welfare than the original platform with an interaction budget linear in platform count. Experiments on synthetic and Amazon-grounded markets show that credibility assessment can improve finite-horizon utility, while its benefits depend on market size and mechanism parameters.
Xin Xu, Ke Cheng, Hao Wang, Yangru Huang, Yanghao Xiao, Zhichao Chen, Zhisheng Zhong, Xun Liu 等 14 位作者
Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while fully evaluating every intermediate version often exhausts the budget before those sequences yield a verified improvement. Inspired by the draft--verify principle of speculative decoding, we propose Speculative Recursive Self-Improvement (SpecRSI), a two-level framework coupling inner-loop agent search with outer-loop improver learning. SpecRSI drafts successors before their predecessors are fully evaluated, while adopting only fully evaluated, admissible versions. In the inner loop, Verification-Aware Tree Search (VATS) allocates the budget between further edits and outstanding checks using the predicted verified return of a continuation. In the outer loop, Group Verification Optimization (GVO) updates the improver from completed searches while keeping the real evaluator fixed. We evaluate SpecRSI on scientific optimization (including active queue management (AQM) for network infrastructure), coding, and general agent-system benchmarks. Under matched evaluation-call budgets, SpecRSI improves scientific terminal gain over Janus by 60.0%--96.3% and area under the budget curve by 32.1%--91.6%, while achieving higher means across all 50 scientific backbone--task pairs and outperforming MetaRSI-v1 by 1.30--2.70 percentage points (pp) in system score across twenty backbones. On instance-level comparisons, it further improves PyBaMM terminal gain by 142.6% and SWE-Pro success by 6.0 pp at 7.0% and 9.2% lower token cost, respectively. These results demonstrate the efficacy of the proposed approach.
Generating humorous memes is a challenging multimodal task that moves beyond direct image-to-caption supervision. It requires a nuanced reasoning over visual content, contextual cues, and subjective humor. To bridge this gap between visual perception and humorous punchline creation, we propose HUMOR}, a novel framework that guides VLMs through hierarchical reasoning and aligns them with group-wise human preferences. First, HUMOR employs a hierarchical, multi-path Chain-of-Thought (CoT): the model begins by identifying a template-level intent, then explores diverse reasoning paths under different contexts, and finally anchors onto a high-quality, context-specific path. This CoT supervision, which traces back from ground-truth captions, enhances reasoning diversity. We further analyze that this multi-path exploration with anchoring maintains a high expected humor quality, under the practical condition that high-quality paths retain significant probability mass. Second, to capture subjective humor, we train a pairwise reward model that operates within groups of memes sharing the same template. Following established theory, this approach ensures a consistent and robust proxy for human preference, even with subjective and noisy labels. The reward model then enables a group-wise reinforcement learning optimization, guaranteeing providing a theoretical guarantee for monotonic improvement within the trust region. Extensive experiments show that HUMOR empowers various VLMs with superior reasoning diversity, more reliable preference alignment, and higher overall meme quality. Beyond memes, our work presents a general training paradigm for open-ended, human-aligned multimodal generation, where success is guided by comparative judgment within coherent output group.
Cao Te, Mengge Xue, Zhenyu Hu, Yuan Chen, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
While advertising is a cornerstone of commercial growth, it is constrained by online violation detection systems that reject non-compliant content at a million-scale daily. Advertisers urgently require automated solutions to rectify these advertisements, especially visual ads, as manual fixing is unscalable. Although recent safety-driven methods can achieve compliance, they typically suffer from over-editing, destroying the original commercial intent and perceptual similarity.To address this, we present SSR-A, a framework tailored for the minimalist rectification of non-compliant image ads.Instead of fine-tuning image editing models directly, SSR-A focuses on translating violation policies into targeted editing instructions.We first introduce a Spatial- and Semantic-Aware Instruction Synthesis Pipeline, where MLLMs synthesize candidate instructions—incorporating spatial grounding and semantic guidance—and select the optimal instruction via multi-dimensional evaluation. Furthermore, we align the model using Curriculum Reinforcement Learning, employing GRPO with multi-faceted rewards to progressively navigate the trade-off between compliance and visual preservation. Extensive experiments and online A/B tests show that SSR-A significantly outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Yuan Chen, Zhenyu Hu, Mengge Xue, Cao Te, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang
Rigorous content moderation is crucial for online advertising but leads to millions of daily rejections. This scale renders manual rectification infeasible, particularly for video advertisements.However, existing safety-driven methods often suffer from aggressive over-editing, which compromises the advertiser’s original semantic intent merely to satisfy compliance.In this work, we target the rectification of textual violations in video ads, covering both speech transcripts and on-screen text. We propose \mathcal{R}^3, a novel framework designed to harmonize compliance with original semantic intent preservation.Our approach integrates three key innovations: (1) an experience-driven data synthesis framework that bootstraps high-quality supervision via group-Relative compliance experience extractor; (2) a curriculum Reinforcement learning strategy with hierarchical rewards designed to enforce compliance while maximizing semantic consistency;and (3) a comprehensive video Rectification framework seamlessly integrating text recognition, rewriting, and re-rendering for industrial deployment. Extensive experiments on industrial datasets and online A/B testing demonstrate that \mathcal{R}^3 significantly outperforms state-of-the-art baselines, achieving an optimal trade-off between violation rectification and intent preservation.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Tianle Xia, Ming Xu, Lingxiang Hu, Yiding Sun, Wenwei Li, Linfang Shang, Liqun Liu, Peng Shu 等 10 位作者
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning.Agentic RAG addresses this by enabling LLMs to dynamically decide when and what to retrieve, but current RL-based training methods suffer from sparse outcome rewards that discard intermediate signals and low sample efficiency where failed samples contribute nothing.We propose Search-P1, a framework that introduces path-centric reward shaping for agentic RAG training, comprising two key components: (1) Path-Centric Reward, which evaluates the structural quality of reasoning trajectories through order-agnostic step coverage and soft scoring that extracts learning signals even from failed samples, and (2) Dual-Track Path Scoring with offline-generated reference planners that assesses paths from both self-consistency and reference-alignment perspectives.Experiments on multiple QA benchmarks demonstrate that Search-P1 achieves significant improvements over Search-R1 and other strong baselines, with an average accuracy gain of 7.7 points.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Liqun Liu, Peng Shu 等 10 位作者
Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72%. A two-week online A/B test demonstrates a 28.6% increase in like rate, a 46.2% decrease in dislike rate, and a 92.7% reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Deyi Ji, Junyu Lu, Xuanyi Liu, Liqun Liu, Hailong Zhang, Peng Shu, Huan Yu, Jie Jiang 等 10 位作者
Online advertising governance faces significant challenges due to the non-stationary nature of regulatory policies, where emerging mandates (e.g., restrictions on education or aesthetic anxiety) create severe label inconsistencies and reasoning ambiguities in historical datasets. In this paper, we propose ARGUS, a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. ARGUS addresses the sparsity of new policy data by employing a three-stage framework: (1) Policy Seeding for initial perception; (2) Adversarial Label Rectification, which utilizes a ”Prosecutor-Defender-Umpire” architecture to resolve conflicts between stale labels and new mandates; and (3) Latent Knowledge Discovery, which employs a tripartite dialectical discussion to unearth sophisticated, “gray-area” violations. By leveraging RAG-enhanced policy knowledge and Chain-of-Thought synthesis as dynamic rewards for reinforcement learning, ARGUS synchronizes its reasoning pathways with evolving regulations. Extensive experiments on both industrial and public datasets demonstrate that ARGUS significantly outperforms traditional fine-tuning baselines, achieving superior policy-adaptive learning with minimal gold data.
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-layers. As MoE architectures have emerged as an efficient method for scaling model capacity without proportionally increasing computation, determining the optimal expert-attention compute ratio becomes critical. We define the ratio r as the fraction of total FLOPs per token dedicated to the expert layers versus the attention layers, and explore how this ratio interacts with the overall compute budget and model sparsity. Through extensive experiments with GPT-style MoE Transformers, we empirically find that the optimal ratio r^\* follows a power-law relationship with total compute and varies with sparsity. Our analysis leads to an explicit formula for r^\*, enabling precise control over the expert-attention compute allocation. We generalize the Chinchilla scaling law by incorporating this architectural parameter, providing a new framework for tuning MoE models beyond size and data. Our findings offer practical guidelines for designing efficient MoE models, optimizing performance while respecting fixed compute budgets.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Weijie Jiang, Gaolei He East China Normal University, Beibei Xiong East China Normal University, Jianlin Wang, Zhengfeng Yang East China Normal University
Autoformalization aims to bridge the gap between human mathematical intuition and formal proof by automating the translation of informal reasoning into machine-verifiable languages. Despite significant breakthroughs catalyzed by Large Language Models (LLMs), autoformalizing Combinatorics remains a formidable challenge due to its intricate structural dependencies and the severe scarcity of high-quality formal datasets. To address these challenges, we propose SAIR-Comb, a Structure-Aware Iterative Refinement framework for Combinatorics powered by Lean 4 and LLMs. SAIR-Comb employs a multi-stage pipeline: first, it performs data augmentation and refinement by rectifying syntactic, semantic, and structural errors, guided by a curated manual combinatorics dataset. The model then undergoes a two-stage training regime: expert iteration with syntactic grounding, followed by reinforcement learning (RL) to align formal reasoning trajectories. Furthermore, we introduce Structural Consistency—a rigorous new metric designed to expose formalizing failures that elude traditional semantic-only evaluations. Experiments demonstrate that SAIR-Comb achieves strong performance on the specialized CombiBench while remaining highly competitive on general-domain benchmarks, including PutnamBench and ProverBench.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zefang Zong Tencent Inc., Dingwei Chen SUN YAT-SEN UNIVERSITY, Yang Li Tencent Inc., Qi Yi University of Science and Technology of China, Bo Zhou, Chengming Li Shenzhen MSU-BIT University, BO Qian Tencent Inc., Peng Chen 等 9 位作者
LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has recently drawn significant research attention as a critical post-training paradigm to further refine these capabilities. In this paper, we present AT²PO (Agentic Turn-based Policy Optimization via Tree Search), a unified framework for multi-turn agentic RL that addresses three core challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization. AT²PO introduces a turn-level tree structure that jointly enables Entropy-Guided Tree Expansion for strategic exploration and Turn-wise Credit Assignment for fine-grained reward propagation from sparse outcomes. Complementing this, we propose Agentic Turn-based Policy Optimization, a turn-level learning objective that aligns policy updates with the natural decision granularity of agentic interactions. ATPO is orthogonal to tree search and can be readily integrated into any multi-turn RL pipeline. Experiments across seven benchmarks demonstrate consistent improvements over the state-of-the-art baseline by up to 1.84 percentage points in average, with ablation studies validating the effectiveness of each component.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Di Zhang, Xun Wu, Shaohan Huang, Lingjie Jiang Peking University, Yaru Hao Microsoft Research Asia, Li Dong Microsoft Research, Zewen Chi Microsoft Research, Zhifang Sui Peking University 等 9 位作者
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for improving reasoning capabilities. However, training RLVR with Mixture-of-Experts (MoE) policies remains fragile and is often prone to reward collapse.We identify a MoE-specific source of instability, referred to as router shift (RS), where changes in expert routing across policy updates exacerbate off-policy mismatch. This effect leads to increasingly volatile importance-ratio signals and bursty clipping behavior, which consistently precede training collapse.Motivated by this diagnosis, we propose Router-Shift Policy Optimization (RSPO). RSPO computes a per-token router-shift ratio conditioned on the previously activated experts, applies stop-gradient and a lower-bound floor, and softly rescales importance ratios prior to clipping and aggregation. This design explicitly accounts for routing-induced distributional drift during off-policy optimization.We evaluate the effect of RSPO under two settings: a synthetic countdown task and real-world reasoning tasks on MATH and Code. Across both settings, RSPO achieves better performance and exhibits greater stability compared to recent MoE-based RLVR methods.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yixia Li, Yaqing Shi, Zhiwen Ruan, Dongdong Zhang Research, Microsoft, Lingjie Jiang Peking University, Shaohan Huang, Yun Chen Shanghai University of Finance and Economics, Guanhua Chen Southern University of Science and Technology 等 9 位作者
Multimodal large language models have advanced rapidly, yet most remain English-centric, as scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of high-quality non-English image–text supervision. Although multilingual text data is abundant, naive textual fine-tuning can disrupt vision–language alignment and induce catastrophic forgetting. We propose Vision-Free Adaptation (VFA), a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone. Specifically, we fine-tune a base LLM on multilingual text data to derive a multilingual task vector, which is then merged with the vision-aligned task vector of an MLLM. Experiments on five MLLMs across six multilingual multimodal benchmarks show consistent improvements while preserving both general multimodal and text-only capabilities. Moreover, VFA attains competitive performance with a fully multimodally trained model using less than 2% of the text data, demonstrating its efficiency and effectiveness.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhicong Li, Lingjie Jiang Peking University, Yulan Hu Alibaba Group, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen Southern University of Science and Technology, Zheng Pan Alibaba Group 等 10 位作者
Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic models, which fail to adapt as the policy evolves. In on-policy RL, the agent’s trajectory distribution and error patterns shift over time, causing stationary critics to become stale and providing feedback of diminishing utility. To address this, we introduce ECHO (Evolving Critic for Hindsight-Guided Optimization), a framework that jointly optimizes the policy and critic through a synchronized co-evolutionary loop. ECHO utilizes a cascaded rollout mechanism where the critic generates multiple diagnoses for an initial trajectory, followed by policy refinement to enable group-structured advantage estimation. We address the challenge of learning plateaus via a saturation-aware gain shaping objective, which rewards the critic for inducing incremental improvements in high-performing trajectories. By employing synchronized dual-track GRPO updates, ECHO ensures the critic’s feedback stays synchronized with the evolving policy. Experimental results show that ECHO yields more stable training and higher long-horizon task success across open-world environments.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表