Rong Fu, Chunlei Meng, Haoyu Zhao, Kun Liu, Simon James Fong
The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.
Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline. While most research focuses on quantization and generation, the representation that bridges the two remains underexplored. Existing representation constructions mainly take two forms: either directly flattening the SID code embeddings into a sequence or merging them into a compact vector via external networks. While effective, they still expose two practical challenges: \textbf{1) Loss of item semantics:} Information lost by quantization or compression needs to be recovered during the representation stage. \textbf{2) Insufficient modeling of structured SID relations:} Intra-item code composition patterns and inter-item prefix-transition patterns are not explicitly preserved for representation and subsequent SID generation. To overcome these challenges, we propose \textbf{ComeIR}, a \textbf{\uline{Co}}nditional \textbf{\uline{me}}mory Enhanced \textbf{\uline{I}}tem \textbf{\uline{R}}epresentation framework that reconstructs SID code embeddings into item-aware inputs and preserves structured SID evidence for prediction. Item-guided Token Scoring estimates the contribution of each SID code using the item embedding employed by the quantizer. Dual-level Conditional Memory captures intra-item prefix composition and inter-item prefix transitions, while Memory Merge integrates these signals into each historical item representation. The Memory-restoring Prediction Head further conditions SID-level prediction on the generated prefix and historical transition evidence. Extensive experiments demonstrate the effectiveness and flexibility of ComeIR, and further reveal scalable gains from enlarging conditional memory.
This paper addresses long-range sensing in bistatic low-Earth-orbit integrated sensing and communication (LEO-ISAC). Conventional OFDM sensing fails in LEO-ISAC because millisecond-scale propagation delays destroy the transmitter--receiver symbol alignment and, with multiple targets, make the receive window longer than the transmitted block. We propose a window-grid (WG) processing framework that exploits the known beam-intersection swath to resolve both problems purely at the receiver, leaving the 3GPP symbol structure unmodified: the swath delay span is folded into cyclic-prefix-sized slices, each handled by one WG. With 103.2 MHz bandwidth at bistatic ranges beyond 640 km, simulations demonstrate meter-level ranging of two targets, and 1000 Monte-Carlo trials over random target--satellite geometries show that, with an ephemeris-based satellite-selection rule, every target is detected with a 90th-percentile range error of 2.4 m.
Mingyu Zhao, Shuhang Lin, Ligong Han, Xiaojing Yu, Zhenting Wang, Yifei Pang, Yang Zhou, Dimitris N. Metaxas
Diffusion language models offer a promising path to efficient agents through parallel token generation. However, efficient interaction requires adapting both where computation is spent and how much text is generated. We introduce a metacognitive controller that guides diffusion generation according to the needs of the current response and the agent's interaction with the environment. It learns when to finalize tokens and how far generation should extend, reducing overall computation within responses. Our controller, a lightweight plug-in for the diffusion backbone, is trained on agent trajectories to balance correctness and generation cost. This approach connects the agent's generation process to the interaction the agent serves. Experiments across five benchmarks demonstrate that our approach reduces inference FLOPs by 20.6% on average compared with the most efficient baseline, while maintaining competitive task accuracy. Ablation studies further validate the effectiveness of our approach.
Xinying Qian, Ying Zhang, Yu Zhao, Xubo Liu, Baohang Zhou, Jeff Z. Pan
Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogeneous information is mixed within coarse-grained memory units; and (2) Organizational Mismatch, where memory structures based primarily on semantic similarity may overlook other associations. To address these challenges, we propose ETAMem, a multi-view memory framework that decouples heterogeneous conversational information and aligns memory representations and organization with its distinct characteristics. Specifically, heterogeneous information parsing extracts atomic memory units and identifies affective information. View-specific memory structuring then organizes these units into three complementary hierarchical views: Event, Affect, and Time. ETAMem incrementally maintains memory structures with adaptively calibrated thresholds. For retrieval, entropy-based retrieval allocates query-specific budgets across views and performs hierarchical search within each view. Experiments on LoCoMo and LongMemEval-S demonstrate that ETAMem outperforms state-of-the-art baselines, achieving relative accuracy improvements of 12.46% and 7.96%, respectively, while maintaining competitive token efficiency. Further analyses demonstrate the complementary benefits of different memory views.
Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Xintong Wang, Chonghan Liu, Shimin Shan, Yichao Du 等 9 位作者
Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost in context length, making long-CoT deployment costly in production. We therefore introduce LISA (Linear-Indexed Sparse Attention), a plug-and-play replacement for self-attention that requires no full pretraining. LISA combines a linear-attention branch for long-range memory with a Lightning Indexer that dynamically selects the most relevant tokens for a sparse self-attention branch. The two branches are fused through a learned gate, so the model retains broad context while focusing computation on informative tokens. We train LISA in two stages. In Stage 1, a linear-attention branch is integrated with sliding-window attention and distilled from a frozen teacher's full-attention distribution. In Stage 2, the Lightning Indexer replaces the static window and is trained with a per-head KL-divergence objective to mimic teacher attention patterns. The resulting model reduces eager-mode self-attention computation from quadratic in sequence length to linear in the number of generated tokens and the selected context budget. Experiments on DeepSeek-distilled Qwen models show that LISA cuts measured eager-mode mean sample latency by 23.9% at 16K context without degrading long-context reasoning quality. Across nine mathematical and code reasoning benchmarks, the gated LISA-1.5B model improves the equal-weight benchmark average by 4.2 percentage points relative to the full-attention baseline.
Yu Zhao, Fan Jiang, Tianle Liu, Bo Zeng, Xintong Wang, Jiaxuan Teng, Yu Liu, Yichao Du
Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from gradient signal attenuation when encountering problems that are either too trivial or overly complex. In these scenarios, the disappearance of inter-group advantages makes the gradient signal susceptible to noise, thereby jeopardizing convergence stability. While variants like DAPO attempt to rectify gradient vanishing, they do not alleviate the substantial computational overhead incurred by exhaustive rollouts on low-utility samples. In this paper, we propose Difficulty-Estimated Policy Optimization (DEPO), a novel framework designed to optimize the efficiency and robustness of reasoning alignment. DEPO integrates an online Difficulty Estimator that dynamically assesses and filters training data before the rollout phase. This mechanism ensures that computational resources are prioritized for samples with high learning potential. Empirical results show that DEPO achieves approximately 1.86x faster rollouts than DAPO in the profiled configuration, while improving benchmark performance over GRPO at comparable training cost. Our approach significantly lowers the computational barrier for training high-performance reasoning models, offering a more sustainable path for reasoning scaling.
Proactive LLM agents anticipate service opportunities from ongoing observations and accumulated history. Existing approaches emphasize recent context or retrieval of related memories, providing limited support for validating recurring behavioral regularities and assessing their applicability to the current event. We propose Proactive Memory (ProactMem), which organizes history into recent events, temporal trajectories, and behavioral regularities. Trajectory facts are checked against source events, and regularities are assessed through historical replay before being matched to current conditions. We also construct ProactiveStream, a longitudinal benchmark covering three application scopes, where agents process isolated event streams chronologically under episode-aware opportunity labels. On ProactiveStream, ProactMem achieves an overall effectiveness (F1) of 52.6%, a 21.4% relative improvement over the strongest of five external baselines. Code is available at: https://anonymous.4open.science/r/ProactMem-5351/.
Learning controllable world dynamics from heterogeneous interaction videos is challenging because robot embodiments use incompatible action spaces, while human videos lack native control labels. We present RynnWorld-Latent, a cross-embodiment video world model that uses the 3D-grounded latent actions introduced by RynnLAM as a shared conditioning interface. This representation enables joint pretraining on human interaction videos, robot demonstrations, and simulation rollouts without requiring a common native action space. Built on a pretrained video transformer, RynnWorld-Latent combines global action tokens with an identity-initialized local pathway that aligns actions with future video latents. We pretrain on 23 datasets comprising approximately 553.5M frames and adapt the model to target robots through post-training. The framework supports two data-generation routes: digital teleoperation uses target robot commands to generate action-video demonstrations, while latent-action synthesis transfers source motion to an edited initial frame and pairs the resulting rollout with retargeted pseudo robot actions. Experiments show improved video prediction metrics on public benchmarks and two real-robot platforms, alongside qualitative action following when different action sequences share the same initial observation. Synthetic mid-training improves policy success rates on LIBERO and LIBERO-Plus, and both generation routes improve real-world policy success rates over real-demonstration-only training in the evaluated settings. These results support universal latent actions as a scalable interface for learning controllable visual dynamics across heterogeneous embodiments.
Scaling model capacity has emerged as an effective approach to overcoming performance bottlenecks in industrial recommender systems. However, repeatedly training new models from scratch requires large amounts of data and substantial training resources. Parameter inheritance provides a promising route for both dense model growth and sparse conversion, yet existing methods for LLMs are primarily designed for static corpora and can suffer sharp performance drops under dynamically evolving recommendation data. To address these challenges, we propose Inherit4Rec, a parameter-inheritance framework that supports both Dense-to-Dense (D2D) growth and Dense-to-Sparse (D2S) conversion. Inherit4Rec-D2D combines hybrid growth with asymmetric training to preserve the forward function at expansion and maintain update continuity. Inherit4Rec-D2S constructs SMoE networks through co-activation-aware partitioning with a load-balancing loss, preserving dense-model capabilities while promoting balanced expert activation. Experiments on KuaiRand-1K and an industrial short-video recommendation dataset show that both transformations consistently outperform the SOTA inheritance baselines across all prediction objectives. These results demonstrate the effectiveness of Inherit4Rec for continual capacity expansion and computation-efficient sparse conversion in industrial recommender systems.
A major challenge facing AI scientific discovery pipelines is how to determine when a generated idea is meaningfully novel. Ideally, novelty checks in these pipelines must be able to reject non-novel ideas while not rejecting too many novel ideas, and they should also be able to distinguish which parts of a proposal are non-novel, as opposed to opaquely discarding entire proposals. We design an analytical framework for evaluation of novelty checks with temporal ground truth at both the proposal- and claim-level, using four datasets of 1,060 proposals built from published papers, reviewer disputes, and generated ideas matching ones the field went on to publish. Auditing existing novelty checks with this framework, we find that checks with high rejection rates on non-novel work also tend to have high false alarms on ideas that are later realized by human researchers, and observe that checks built to evaluate proposals as a whole can point to claim-level prior art only by rejecting the whole proposal. We therefore introduce ClaimNov, a fine-grained, interpretable claim-level novelty module. ClaimNov catches 97% of disguised papers at a 1.5% false-alarm rate, and its claim-level novelty profile cuts the LLM judge's false alarms from 11.8% to 1.5%. Because its verdict rests on claim-level evidence, ClaimNov also keeps proposals that build on established contributions, rejecting only 3% of ICLR-accepted proposals with a reviewer-disputed contribution and keeping 91 of 100 novel proposals with one spliced prior contribution, against 76 for the strongest existing check. Code and data are available at https://github.com/emmatliu/claimnov.
Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies. In this work, we propose a hybrid framework in which a text-based corpus identifies the leading factors of a failure mode. Physics-based models then quantify how likely that failure is at a stated operating point. Ordered causal chains extracted from 56,202 American accident reports with a local large language model aggregate into a causation knowledge graph. On an evaluation sample of 2,000 reports, the chains recover 90.8% of investigator-flagged causes. Each physical factor whose drivers the record carries receives an occurrence model calibrated to the accident population. A leaky noisy-OR fitted to the corpus combines the factors into a failure mode probability that supports intervention. For engine power loss, the carburetor icing model separates 1,205 icing accidents from other accidents using temperature and dewpoint alone, reaching 0.61 in area under the receiver operating characteristic curve against a density ratio ceiling of 0.64. Routine weather hours give no valid control, because flying concentrates in fair weather. On later years the physics adds 0.03 to that area for occurrence and nothing for severity, so its value lies in interpretability. On four named accidents, abduction gives a probability of necessity of 0.29 to 0.50 for the heat omission, under monotonicity. The Fast Causal Inference algorithm does not license the largest backdoor adjustment on the learned networks.
Shuheng Chen, Namratha Patil, Haonan Pan, Angel Hsing-Chi Hwang University of Southern California, Yao Du University of Southern California, Ruishan Liu University of Southern California, Jieyu Zhao University of Southern California
Clinical decision-making requires synthesizing heterogeneous evidence, including patient histories, clinical guidelines, and trajectories of comparable cases. While large language models (LLMs) offer strong reasoning capabilities, they remain prone to hallucinations and struggle to integrate long, structured medical documents. We present MED-COPILOT, an interactive research prototype for evidence-aware clinical reasoning, designed to help clinicians and medical trainees inspect guideline-level and patient-level evidence. MED-COPILOT combines guideline-grounded GraphRAG retrieval with hybrid semantic-keyword similar-patient retrieval to support transparent and evidence-aware clinical reasoning. The system builds a structured knowledge graph from WHO and NICE guidelines, applies community-level summarization for efficient retrieval, and maintains a 36,000-case similar-patient database derived from SOAP-normalized MIMIC-IV notes and Synthea-generated records.We evaluate our framework on clinical note completion and medical question answering, and demonstrate that it consistently outperforms parametric LLM baselines and standard RAG, improving generation fidelity and benchmark QA accuracy. The full system is available at https://huggingface.co/spaces/shuhengc/MED-COPILOT, enabling users to inspect retrieved evidence, visualize token-level similarity contributions, and conduct guided follow-up analysis. Our results suggest a practical and interpretable approach to integrating structured guideline knowledge with patient-level analogical evidence for clinical LLMs.
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 3: System Demonstrations) · 2026 · 正式发表
Xue Jiang, Ge Li Peking University, Jiaru Qian, Xianjie Shi, Chenjie Li Peking University, Hao Zhu, Ziyu Wang Peking University, Jielun Zhang Peking University 等 14 位作者
Large language models (LLMs) excel at general programming but struggle with domain-specific software development. This gap motivates research into domain specialization methods that enable LLMs to learn and utilize domain knowledge and data. However, existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge, lacking explicit knowledge corpora for developing domain specialization methods. To this end, we present KOCO-bench, a novel benchmark designed for evaluating domain specialization methods in real-world software development. KOCO-bench contains 6 emerging domains with 11 software frameworks and 25 projects, featuring curated knowledge corpora alongside multi-granularity evaluation tasks including domain code generation (from function-level to project-level with rigorous test suites) and domain knowledge understanding (via multiple-choice Q A). Unlike previous benchmarks that only provide test sets for direct evaluation, KOCO-bench requires acquiring and applying diverse domain knowledge (APIs, rules, constraints, etc.) from the corpora to solve evaluation tasks. Our evaluations reveal that KOCO-bench poses significant challenges to state-of-the-art LLMs. Even with domain specialization methods (e.g., SFT, RAG, kNN-LM) applied, improvements remain marginal. Best-performing coding agent, Claude Code, achieves only 34.2%, highlighting the urgent need for more effective domain specialization methods. We release KOCO-bench, evaluation code, and baselines to advance further research at https://github.com/jiangxxxue/KOCO-bench.
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
Taiwei Shi, Zhuoer Wang Amazon, Longqi Yang Microsoft, Ying-Chun Lin Amazon, Zexue He, Mengting Wan Microsoft, Pei Zhou Microsoft, Sujay Kumar Jauhar Microsoft Research 等 15 位作者
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive nature, inherent subjectivity, misalignment with real-world user preferences, and the risk of feedback loops that amplify model biases. To overcome these limitations, we introduce WildFeedback, a novel framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically. Given a corpus of multi-turn user-LLM conversation, WildFeedback identifies and classifies user feedback to LLM responses between conversation turns. The user feedback is then used to create examples of preferred and dispreferred responses according to users’ preference. Our experiments demonstrate that LLMs fine-tuned on WildFeedback dataset exhibit significantly improved alignment with user preferences, as evidenced by both traditional benchmarks and our proposed checklist-guided evaluation. By incorporating in-situ feedback from actual users, WildFeedback addresses the scalability, subjectivity, and bias challenges that plague existing approaches, marking a significant step toward developing LLMs that are more responsive to the diverse and evolving needs of their users.
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
Feiyu Zhao, Yiming Chen, Wenhuan Lu Tianjin University, China, Daipeng Zhang, Xianghu Yue, Jianguo Wei Tianjin University
Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically unsupported, remains largely underexplored in the audio domain. Existing hallucination benchmarks mainly focus on text or vision, while the few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. We therefore introduce HalluAudio, the first large-scale benchmark for evaluating hallucinations across speech, environmental sound, and music. HalluAudio comprises over 5K human-verified QA pairs and spans diverse task types, including binary judgments, multi-choice reasoning, attribute verification, and open-ended QA. To systematically induce hallucinations, we design adversarial prompts and mixed-audio conditions. Beyond accuracy, our evaluation protocol measures hallucination rate, yes/no bias, error-type analysis, and refusal rate, enabling a fine-grained analysis of LALM failure modes. We benchmark a broad range of open-source and proprietary models, providing the first large-scale comparison across speech, sound, and music. Our results reveal significant deficiencies in acoustic grounding, temporal reasoning, and music attribute understanding, underscoring the need for reliable and robust LALMs.
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
Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang City University of Hong Kong, Pengyue Jia City University of Hong Kong, Yingyi Zhang, Haiying He, Mengyang Ma 等 12 位作者
Personalized Large Language Models (PLLMs) aim to align model outputs with individual user preferences, a crucial capability for user-centric applications. However, the prevalent approach of fine-tuning a separate module for each user faces two major limitations: (1) storage costs scale linearly with the number of users, rendering the method unscalable; and (2) fine-tuning a static model from scratch often yields suboptimal performance for users with sparse data. To address these challenges, we propose MTA, a Merge-then-Adapt framework for PLLMs. MTA comprises three key stages. First, we construct a shared Meta-LoRA Bank by selecting anchor users and pre-training meta-personalization traits within meta-LoRA modules. Second, to ensure scalability and enable dynamic personalization combination beyond static models, we introduce an Adaptive LoRA Fusion stage. This stage retrieves and dynamically merges the most relevant anchor meta-LoRAs to synthesize a user-specific one, thereby eliminating the need for user-specific storage and supporting more flexible personalization. Third, we propose a LoRA Stacking for Few-Shot Personalization stage, which applies an additional ultra-low-rank, lightweight LoRA module on top of the merged LoRA. Fine-tuning this module enables effective personalization under few-shot settings. Extensive experiments on the LaMP benchmark demonstrate that our approach outperforms existing SOTA methods across multiple tasks. Our code is also available.
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
Derong Xu City University of Hong Kong and University of Science and Technology of China, Shuochen Liu University of Science and Technology of China, Pengfei Luo, Pengyue Jia City University of Hong Kong, Yingyi Zhang, Yi Wen, Yimin Deng City University of Hong Kong and Xi'an Jiaotong University, Wenlin Zhang City University of Hong Kong 等 11 位作者
Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static, hand-crafted update rules; although reinforcement learning (RL)-based agents learn memory updates, sparse outcome rewards provide weak supervision, resulting in unstable long-horizon optimization. Drawing on memory schema theory and the functional division between prefrontal regions and hippocampus regions, we introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update. In the first stage, we propose Memory Guideline Induction to optimize a global guideline via contrastive feedback interpreted as textual gradients; in the second stage, Guideline-Aligned Memory Policy Optimization uses the induced guideline to define structured process rewards and performs multi-turn RL to learn a guideline-following memory evolution policy. We evaluate on three personalization memory benchmarks, covering explicit and implicit preferences as well as different sizes and noise levels, and observe consistent improvements over strong baselines with favorable robustness, transferability, and efficiency[https://github.com/Applied-Machine-Learning-Lab/ACL2026_MemCoE].
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
Xiangyu Zhao, Wanghan Xu Shanghai Jiaotong University, Bo Liu, Yuhao Zhou, Fenghua Ling Shanghai Artificial Intelligence Laboratory, Ben Fei, Xiaoyu Yue University of Sydney, Lei Bai Shanghai AI Laboratory 等 10 位作者
The rapid advancement of multimodal large language models (MLLMs) offers new opportunities for complex scientific challenges, yet their application in earth science—especially at the graduate level—remains underexplored due to a lack of benchmarks reflecting the depth and complexity of geoscientific reasoning. Existing datasets often rely on synthetic data or simple figure-caption pairs, failing to capture the nuanced reasoning required for real-world applications. To address this, we introduce MSEarth, a multimodal scientific dataset and benchmark curated from high-quality, open-access publications. Covering the five major spheres of Earth science—atmosphere, cryosphere, hydrosphere, lithosphere, and biosphere—MSEarth features over 289K figures with refined captions enriched by contextual discussions and reasoning from the original papers. The benchmark supports tasks such as scientific figure captioning, multiple choice questions, and open-ended reasoning, providing a scalable, high-fidelity resource for developing and evaluating MLLMs in scientific reasoning.
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
Deming Ding Large Language Model Algorithm Engineer, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo Fudan University, Weiyu Cheng Minimax Ai 等 15 位作者
Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this gap, we introduce OctoBench, which benchmarks scaffold-aware instruction following in repository-grounded agentic coding. OctoBench includes 34 environments and 217 tasks instantiated under three scaffold types, and is paired with 7,098 objective checklist items. To disentangle solving the task from following the rules, we provide an automated observation-and-scoring toolkit that captures full trajectories and performs fine-grained checks. Experiments on eight representative models reveal a systematic gap between task-solving and scaffold-aware compliance, underscoring the need for training and evaluation that explicitly targets heterogeneous instruction following. We will release the benchmark to support reproducible benchmarking and to accelerate the development of more scaffold-aware coding agents.
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
Xinying Qian, Ying Zhang Nankai University, Xuhui Sui, Yu Zhao Nankai University, Baohang Zhou Tiangong University, Jeff Z. Pan University of Edinburgh, University of Edinburgh
Temporal reasoning remains a critical challenge for large language models (LLMs), particularly when it requires encompassing relational dependencies and numerical constraints. Yet, existing benchmarks largely overlook the joint consideration of these two dimensions and primarily rely on single-task evaluation paradigms, making it difficult to assess whether correct answers reflect grounded reasoning or arise from superficial statistical recall. To address these gaps, we introduce TNR, a benchmark designed to evaluate both Temporal Numerical and Relational reasoning. We propose a bi-directional evaluation framework consisting of forward generation via Question Answering (QA) and backward verification via Fact Verification (FV). By measuring the alignment between QA and FV, we introduce a Consistency Rate to quantify the robustness of reasoning across these two directions. Experiments on a range of LLMs reveal notable discrepancies between QA and FV performance, particularly in numerical and interval-based tasks. Moreover, our bi-directional error analysis demonstrates that these inconsistencies often stem from heuristic shortcuts and statistical co-occurrences rather than grounded logical deduction, flaws that are frequently masked in standard single-task evaluations.
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
Sheng Zhang, Junyi Li, Yingyi Zhang, Pengyue Jia City University of Hong Kong, Yichao Wang, Xiaowei Qian City University of Hong Kong, Wenlin Zhang City University of Hong Kong, Maolin Wang 等 10 位作者
Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative think–search loop accumulates long system memories, leading to memory dilution problem. In addition, existing memory management methods struggle to capture fine-grained semantic relations between queries and documents and often lose substantial information. Therefore, we propose MemSearch-o1, an agentic search framework built on reasoning-aligned memory growth and retracing. MemSearch-o1 dynamically grows fine-grained memory fragments from memory seed tokens from the queries, then retraces and deeply refines the memory via a contribution function, and finally reorganizes a globally connected memory path. This shifts memory management from stream-like concatenation to structured, token-level growth with path-based reasoning. Experiments on eight benchmark datasets show that MemSearch-o1 substantially mitigates memory dilution, and more effectively activates the reasoning potential of diverse LLMs, establishing a solid foundation for memory-aware agentic intelligence.
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
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao Beijing University of Post and Telecommunications, YiJie Chen 等 10 位作者
In knowledge-intensive creative tasks, Large Language Models (LLMs) often generate outputs that extend beyond established knowledge, making direct verification against current evidence impractical. Unlike factual hallucinations checked against ground truth, such outputs arise naturally in creative generation, where extending beyond current knowledge is often the goal. Yet prior work debates whether hallucination should be suppressed or embraced without empirically analyzing this unverifiable subclass. On the ideation evaluation side, existing work focuses on individual outputs without characterizing the unverifiable space as a whole. To address this gap, we propose a novelty-verifiability characterization that distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Region B), and study it through a conceptual creation task where LLMs synthesize novel scientific concepts. Through 32,400 generations across three technical domains and 1,080 human judgments, we find that Region A is non-negligible (4.7%) and robust, persisting across generation strategies, models, domains, and embedding choices. A retrospective recovery experiment further shows that LLMs can approximate post-cutoff scientific concepts in controlled combinatorial settings. Our findings suggest that the unverifiable space is not uniformly noise but exhibits empirically distinguishable internal structure, providing an empirical basis for more selective hallucination governance.[https://github.com/YuLab1/llm-concept-creation]
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
Muyang Li, Runze Wu IROOTECH TECHNOLOGY, Xiangyu Zhao City University of Hong Kong, Bo Han, Daoyi Dong University of Technology Sydney, Tongliang Liu University of Sydney and RIKEN
The post-training stage of Large Language Models (LLMs) typically involves Supervised Fine-Tuning (SFT) followed by preference alignment to ensure LLM to generate safe, helpful, and instruction-aligned content. The SFT model critically serves as both the initialization and reference model for subsequent preference alignment. However, an essential yet often neglected question is the optimal selection of the SFT checkpoint for this role. We show that checkpoint selection substantially affects final performance, and that the common practice of choosing the minimum validation-loss checkpoint often fails, due to a fundamental conflict between SFT’s focus on imitation and alignment’s goal of response discriminability. To this end, we propose RewardRank, a simple, effective, training-free metrics for estimating initial implicit alignment between reference model and preference objective. Empirical evidence suggests that, using our selected model as reference can gain up to 67.6% relative increase on length-controlled win rate on the popular Zephyr recipe comparing to baselines.
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
Yulong Wang Beijing University of Posts and Telecommunications, Siyu Zhao
Parameter-efficient fine-tuning (PEFT) must balance effectiveness and efficiency: low-rank methods can be costly, while global representation edits often underfit token-level contexts. We propose Token-Aware Representation Editing (TARE), a PEFT method that performs fine-grained, token-specific edits with a small additional inference overhead and minimal tuning.After each FFN block in a transformer-like model, we adopt a lightweight selector that scores a small pool of hidden representation editors for each token, activates only the top-k editors, and mixes their element-wise scaling/bias updates. This design achieves superior performance while maintaining computational efficiency, yielding a more favorable Pareto frontier compared to state-of-the-art (SOTA) methods.Across LLaMA-3-8B (eight knowledge reasoning and seven mathematical reasoning tasks) and RoBERTa-base/large (GLUE), TARE outperforms SOTAs (LoRA, DoRA, MiLoRA, LoReFT, and RED), achieving 86.7% (knowledge reasoning), 76.7% (mathematical reasoning), and 88.3% (GLUE) while tuning only 0.0392% of parameters using about 20 GiB peak GPU memory during training.An implementation is available at: https://github.com/PatriciaPulec/tare.
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
Pengyue Jia City University of Hong Kong, Yingyi Zhang, Xiangyu Zhao City University of Hong Kong, Sharon Li
Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with spatial world knowledge. Despite recent advances in large vision-language models (LVLMs), existing evaluation paradigms remain largely outcome-centric, relying on static datasets and predefined labels that are conceptually misaligned with open-world geographic inference. Such outcome-centric evaluations often focus exclusively on label matching, leaving the underlying linguistic reasoning chains as unexamined black boxes. In this work, we introduce GeoArena, a dynamic, human-preference-based evaluation framework for benchmarking open-world geographic reasoning. GeoArena reframes evaluation as a pairwise reasoning alignment task on in-the-wild images, where human judges compare model-generated explanations based on reasoning quality, evidence synthesis, and plausibility. We deploy GeoArena as a public platform and benchmark 17 frontier LVLMs using thousands of human judgments, which complements existing benchmarks and supports the development of geographically grounded, human-aligned AI systems. We further provide detailed analyses of model behavior, including reliability of human preferences and factors influencing judgments of geographic reasoning quality. We open-source GeoArena to foster future research.
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
Zheyuan Liu University of Notre Dame, Yixin Wan University of California, Los Angeles, Kai-Wei Chang University of California, Los Angeles, Meng Jiang University of Notre Dame, Jieyu Zhao University of Southern California, Nouha Dziri Cohere Labs, Yuning Mao Meta Superintelligence Labs, Jia-Chen Gu University of California, Los Angeles 等 9 位作者
Controlling the knowledge and behavior of generative AI systems, including large language models (LLMs), multimodal LLMs (MLLMs), and text-to-image (T2I) models, has become critical as they are increasingly used in safety-sensitive and socially impactful applications. These models often encode unintended, biased, or private content, leading to harmful or unethical outputs. Post-training knowledge control has thus emerged as a practical framework for selectively modifying or removing model behaviors without full retraining, offering scalable and interpretable interventions for improving safety, privacy, and fairness. This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods, bridging research insights with real-world practices from both academia and industry. We cover: (i) key motivations and failure modes, such as harmful generation and stereotype reinforcement; (ii) core methods such as machine unlearning, knowledge editing, and inference-time interventions for targeted behavior adjustment; and (iii) evaluation protocols for balancing forgetting, retention, and fairness. Case studies will span text and vision–language generation, including privacy preservation, bias mitigation, and factual correction.
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 5: Tutorial Abstracts) · 2026 · 正式发表