Generalist robot policies are trained on static offline datasets, yet physical manipulation unfolds sequentially across stages. Because a weakness in a downstream stage remains unobservable until the policy passes earlier ones, each resolved bottleneck exposes the next hidden failure mode. This staged structure calls for Recursive Self-Improvement (RSI), in which a policy iteratively executes, diagnoses failures, and updates itself. Moreover, because task completion behaves like a product of stage-level pass rates, recursive gains can multiply across generations. In physical environments, three bottlenecks obstruct compounding: terminal execution feedback rarely localizes the stage that caused a failure, failed trajectories do not supply the corrective action, and updating shared parameters can degrade previously mastered skills. We propose Compounding Physical RSI, a self-evolving policy framework that turns execution failures into heritable capability. First, automated capability-gap assessment traces failed rollouts to the task stage where progression breaks down and formulates a structured improvement objective. Second, conditioned on this objective, our remedy stage curates validated, stage-relevant experience and refines the policy via behavior-regularized offline reinforcement learning, without requiring costly online rollouts at each optimization step. Third, to safeguard existing skills, our retention stage constructs weight-space candidates between the inherited reference policy and the refined policy, evaluates them across the task suite, and promotes the best candidate as the reference state for the next generation. Evaluated across all 42 tasks of the RoboDojo-Sim benchmark, CSU-AI-07 ranks first on the leaderboard with a three-seed mean Overall Score of 26.15 and Success Rate of 20.70%, outperforming the next-best entry by 5.92 points and 5.82 percentage points.
Qazi Mamunur Rashid, Xuan Yang, Zhengzhe Yang, Yanzhou Pan, Erin van Liemt, Darlene Neal, Kshitij Pancholi
Recent advancements in generative AI facilitate large-scale synthetic data genera- tion for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSyn, an evidence-grounded methodology that generates socially relevant syn- thetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs, NodeSyn elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models.
Proactive query recommendation aims to suggest relevant search queries to users on the homepage of local service apps. Unlike conventional recommendation over a fixed item set, this requires open-set generation from a vocabulary of millions, where outputs must simultaneously align with user preference, match fine-grained spatiotemporal context, cover long-tail intents, and provide diverse alternatives within a few candidate slots. Existing approaches address these axes in isolation: standard tokenization suppresses long-tail queries, coarse location encoding misses fine-grained geographic demand, generic preference optimization fails to align with production impression-click distributions, and standard beam search collapses to near-duplicate outputs. We present SPADE (Spatiotemporal Preference Alignment and Diversity Enhancement), an end-to-end generative framework that jointly optimizes the generation space, contextual representation, preference distribution, and output slate quality through four components: Objective-Aligned BPE (OA-BPE) aligns subword merging with business value signals to boost long-tail query generation probability; Spatio-Temporal Adaptive Representation (STAR) replaces coarse location tokens with continuous multi-scale encodings and soft gating for precise spatiotemporal grounding; MARS-DPO (Multi-dimensional Adaptive Reward Sampling DPO) combines cross-domain pre-training with preference alignment on production impression-click data via composite rewards and adaptive hard negative sampling; and Sigmoid Diversity Beam Search (SDBS) improves intent coverage without sacrificing recall. Offline experiments on large-scale production data show that SPADE outperforms the strongest generative baseline by +5.6% HR@5, -40.3% GeoC@5, and +1.9% Exec@5. A one-week online A/B test confirms production impact: +1.88% Module CTR, +0.177% Search Volume, and +0.105% Search DAU.
Muon has recently shown strong empirical performance in training Transformer-based large language models (LLMs), yet its optimization dynamics remain poorly understood from a theoretical perspective. In this paper, we analyze the training dynamics of Muon for next-token prediction (NTP) in Transformers. The training procedure consists of two phases: the preprocessing phase learns the output-value component, while the main phase learns the key-query component. For the preprocessing phase, we characterize the optimization trajectory exactly and show that the normalized spectral margin is optimal after each update. For the main phase, we establish nonasymptotic convergence rates for the training loss and the normalized margin gap under softmax attention. These results suggest that Muon's update rule can help models efficiently learn which tokens matter for prediction, offering a possible explanation for its strong performance in large language model training. The learned weight structure also yields a generalization guarantee for unseen contexts. Furthermore, we validate our theoretical insights with experiments on next-token prediction tasks.
Tianqi Gao, Chenxu Wang, Wenxuan Yang, Yueqi Mou, Biao Tang, Ming Liu, Peng Yan
Recommender systems are widely used in e-commerce and content platforms, where improvement requires repeated model design, training optimization, and experimental validation. Large language model (LLM) agents increasingly automate this development cycle. Sustained autonomous improvement requires agents to improve both recommendation models and their development workflows. However, task-performance-driven approaches select updates mainly by candidates' final scores, without a separate optimization signal for experimentation quality. We therefore present DualEvolve, a dual-level framework that co-evolves recommendation mechanisms and agent orchestration toward recursive self-improvement. Inner evolution revises model and training code using task feedback to improve recommendation performance. Outer evolution scores the inner-loop experimental process, updates harness and skill rules using these scores and execution traces, and adjusts orchestration choices based on next-round scores to improve the quality of subsequent experiments. Experiments on MovieLens-1M and three Amazon Reviews 2023 subsets cover four recommendation methods and 16 settings. DualEvolve achieves higher test means than Base, OpenEvolve, and DeepEvolve in all 64 setting-metric comparisons, with macro-averaged relative gains over DeepEvolve of 7.6% (HR@5) and 9.0% (NDCG@5).
Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding, retrieval, or generation. We introduce EvalMem, an operation-level diagnostic framework with three parallel Examiners. For each query, the Encoding Examiner checks whether the target fact is stored, the Retrieval Examiner assesses whether the native retriever returns usable evidence, and the Generation Examiner tests whether the model can answer from oracle evidence. Their outputs form fine-grained multi-label defect codes. To improve store-level diagnosis, we adapt agentic RAG with a recall-first strategy that searches using both the query and source evidence, increasing recall of present evidence on LoCoMo from 70.2% to 95.6%. Evaluations of seven memory systems on LoCoMo, LongMemEval-S, and dynamic DynaMem-Bench identify retrieval as the most frequently attributed failure layer; in default LoCoMo, retrieval defects reach 22.1%, compared with 7.7% for encoding and 6.5% for generation. Guided by this diagnosis, MemWiki, a search-friendly auxiliary structure built from each system's memory export, improves mean accuracy by 2.5 and 2.3 percentage points on LoCoMo and LongMemEval-S, respectively.
Coding-agent services are priced by the model they claim, making the verification of such model claims crucial for their users. In this paper, we reveal that existing model auditing methods rely on a latent assumption that the deployment is static, i.e., the claimed model is always served in one reference configuration. This assumption does not hold for coding-agent services, whose providers may legitimately change the sampling preset, the reasoning mode or the system prompt without changing the model. As a result, existing methods either falsely accuse honest providers or miss cheap derivatives of the claimed model. To address this problem, we propose a certified model-claim verification method (dubbed CertClaim). Instead of testing the service against one reference deployment, we make the authorized deployments part of the claim and test whether some authorized deployment explains all the evidence of the service, by calibrating multiple evidence channels in every authorized deployment and fusing them within each deployment. We provide theoretical analyses of its false-accusation rate and detection condition. Extensive experiments on eight claims, two agent harnesses and three task suites verify the effectiveness of CertClaim, which is valid in every setting while separating substitutes far better than existing methods, as well as its resistance to potential adaptive attacks.
Jing Zhang, Ganxuan Yang, Yifei Yang, Siqi Wen, Baiyan Li, Zhengyang Qiu, Hasan Ahmed, Muhammad Bilal
Searchable Encryption (SE) enables users to query outsourced encrypted data while preserving data confidentiality. However, most efficient schemes still leak the search pattern and access pattern, which may allow an honest-but-curious cloud server to infer query contents, user interests, or returned records from repeated searches and observed results. Existing pattern-hiding solutions mainly target keyword queries and do not naturally support Boolean range queries over encrypted spatial data. This paper presents BRASP, a searchable encryption scheme for Boolean range queries over encrypted spatial data. BRASP combines Hilbert-curve-based prefix encoding with encrypted prefix--ID and keyword--ID inverted indexes to support efficient spatial range filtering and conjunctive keyword matching. To hide the search pattern and access pattern under a dual-server setting, BRASP integrates index shuffling for encrypted keyword and prefix entries with ID-field redistribution across two non-colluding cloud servers. BRASP also supports dynamic updates and achieves forward security. We formalize the security of BRASP through confidentiality, shuffle indistinguishability, query unforgeability, and forward-security analyses, and we evaluate its performance experimentally on a real-world dataset. The results show that BRASP effectively protects query privacy while incurring relatively low computation and communication overhead. To facilitate reproducibility and further research, the source code of BRASP is publicly available at https://github.com/Egbert-Lannister/BRASP
Hidden rounding carries dependencies through integer memory. We study finite-memory feedback with predictable inputs that differ by one on at most $C$ releases and with every output public. A shared preparation constrains future branches until a sequence of common-input releases synchronizes the conditional registers. Preserving those constraints yields exact finite-law compilation, polynomial in support width for fixed memory and participation budgets, with constructive discrete-Gaussian transfer and calibration. A commitment hierarchy quantifies the loss from releasing dependencies early and becomes exact at depth $mC$ for memory $m$. Strict examples include three levels with one participation and a discrete-Gaussian calibration gap exceeding 0.23. Charging actual preparation time gives a privacy resource law with a square-root remainder and a leading coefficient computable in polynomial bit cost at fixed parameters. Lean refinements cover the first-order privacy analysis and binary value algorithm; separate lemmas check finite-memory algebra and paths. Certificates establish multi-memory calibration and resource effects; workload comparisons include a finite-memory prefix-error lower bound.
Zhixuan Yang, Fu Zhang Northeastern University, Huangming Xu, Jingwei Cheng Northeastern University, China
Cross-document Relation Extraction (CodRE) requires reasoning over scattered evidence to identify relations between target entities across multiple documents. Existing methods indiscriminately fuse target entities and the intermediate bridge entities that link them into a unified representation. This leads to intermediate evidence that often aligns with only one side of the entity pair, resulting in one-sided relation transfer contextual bias and incomplete reasoning chains. Moreover, these methods typically employ a global threshold to determine relation existence for all entity pairs, limiting the model’s reasoning performance.To address these issues, we propose DEBAR (Dual-stream Entity Bias Reduction), a framework designed to explicitly decouple and preserve bidirectional bridge evidence, combined with a novel dynamic loss optimization objective. Specifically, DEBAR employs a bridge-aware input construction strategy and a dual-stream graph reasoning network to separately encode head and tail contexts, preventing semantic interference while capturing global dependencies through iterative message passing. Furthermore, we introduce a curriculum-aware ranking optimization objective that progressively tightens classification constraints to stabilize training and enforce discriminative decision boundaries. Experiments on the CodRE benchmarks show that DEBAR achieves state-of-the-art performance while effectively mitigating cross-document contextual bias. Moreover, extensive experiments on our proposed loss across backbones confirm its generalization, suggesting it as a reliable replacement for existing CodRE losses. Code is available at https://github.com/newyuyou/DEBAR.
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
Huangming Xu, Fu Zhang Northeastern University, Zhixuan Yang, Lu Zhang, Jingwei Cheng Northeastern University, China
Document-level relation extraction (DocRE) aims to determine which relations hold between a given entity pair within a document. As a multi-label classification task, the most commonly adopted paradigm introduces a learnable threshold to distinguish positive and negative classes for an entity pair. Under this paradigm, existing losses decouple the optimization into independent positive and negative losses, which interact solely with a shared threshold. This leads to two inherent limitations: (i) threshold instability caused by conflicting gradient updates from the decoupled losses; and (ii) optimization bias exacerbated by the severe imbalance between limited positive samples and abundant negative samples inherent in DocRE, which makes the model more likely to predict that no relation exists.To address these issues, we propose the Adaptive-Threshold Global Loss (ATGL). Unlike prior work, ATGL integrates positive, negative, and threshold optimization into a unified logit space and explicitly enforces ranking constraints on their contributions to the objective. Furthermore, ATGL incorporates an imbalance-aware optimization mechanism, thereby effectively addressing the severe class imbalance in DocRE. Our ATGL serves as a general optimization objective that can be readily applied to different DocRE models. Experiments on four datasets show that ATGL outperforms other DocRE losses and achieves state-of-the-art results, while consistently improving the performance of existing DocRE models. Code is available at https://github.com/xhm-code/ATGL.
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
While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought (CoT) reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models. However, achieving both domain performance and cross-domain generalization remains challenging. Existing approaches typically restrict students to following a single golden rationale and treat different reasoning paths independently. Due to distinct inductive biases and intrinsic preferences, alongside the student’s evolving capacity and reasoning preferences during training, a teacher’s “optimal” rationale could act as out-of-distribution noise. This misalignment leads to a degeneration of the student’s latent reasoning distribution, causing suboptimal performance. To bridge this gap, we propose MIND, a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction. We synthesize diverse teacher perspectives through a novel “Teaching Assistant” network. By employing a novel Feedback-Driven Inertia Calibration mechanism, this network utilizes inertia-filtered training loss to align supervision with the student’s current adaptability, effectively enhancing performance while mitigating catastrophic forgetting. Extensive experiments demonstrate that MIND achieves state-of-the-art performance on both in-distribution and out-of-distribution benchmarks, and our sophisticated latent space analysis further confirms the mechanism of reasoning ability internalization.
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
Weicong Liu, Zixuan Yang, Yibo Zhao East China Normal University, Xiang Li East China Normal University
Reviewer assignment is increasingly critical yet challenging in the LLM era, where rapid topic shifts render many pre-2023 benchmarks outdated and where proxy signals poorly reflect true reviewer familiarity. We address this evaluation bottleneck by introducing LR-bench, a high-fidelity, up-to-date benchmark curated from 2024–2025 AI/NLP manuscripts with five-level self-assessed familiarity ratings collected via a large-scale email survey, yielding 1,055 expert-annotated paper–reviewer–score annotations. We further propose a reviewer-centric ranking framework that distills each reviewer’s recent publications into compact keyword-based profiles and fine-tunes an embedding model with weak preference supervision constructed from heuristic retrieval signals, enabling to match each manuscript against a reviewer profile directly. Across the LR-bench and the CMU gold-standard dataset, our approach consistently achieves state-of-the-art performance, outperforming strong embedding baselines by a clear margin. We release LR-bench at https://huggingface.co/datasets/Gnociew/LR-bench, and an github repository at https://github.com/Gnociew/RATE-Reviewer-Assignment.
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