Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline and curate two high-quality datasets, Gen-Searcher-SFT-10k and Gen-Searcher-RL-6k, containing diverse search-intensive prompts and corresponding ground-truth synthesis images. We further introduce KnowGen, a comprehensive benchmark that explicitly requires search-grounded external knowledge for image generation and evaluates models from multiple dimensions. Based on these resources, we train Gen-Searcher with SFT followed by agentic reinforcement learning with dual reward feedback, which combines text-based and image-based rewards to provide more stable and informative learning signals for GRPO training. Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE. We hope this work can serve as an open foundation for search agents in image generation, and we fully open-source our data, models, and code.
World Action Models (WAMs) can condition robot actions on generated visual futures, but this additional context is neither cost-free nor uniformly beneficial. We examine what a predicted future actually changes: the action delta $Δa$ between the future-conditioned and future-free execution paths of the same model. Under a shared WAM checkpoint, this delta barely shifts average benchmark success ($+0.8$ points on LIBERO, $-0.8$ on RoboTwin~2.0), while generating visual futures increases inference latency by 1.7--1.9$\times$. These aggregate metrics conceal a concentrated failure mode that we term \emph{future-induced negative transfer}: while predictive deltas benefit long-horizon tasks ($+2.4$ points on LIBERO-Long) and remain negligible on most routine manipulations, they induce severe degradation on precision tasks---with \emph{Press Stapler} and \emph{Place Can Basket} losing 54.0 and 34.0 points, recurring as top failure modes across independently trained WAM variants. We introduce \textbf{Utility-WAM} for in-place correction of future-conditioned control. Its primary learning component is a residual adapter that repairs future-induced velocity deltas under a frozen shared WAM by aligning them with ground-truth dynamic guidance and penalizing excess error beyond the future-free baseline. The adapter selectively eliminates the majority of severe task drops (reducing losses to 6.0 and 14.0 points) while preserving long-horizon foresight. To eliminate superfluous video computation, a lightweight pre-generation gate reuses counterfactual action outcomes to selectively bypass video generation on 75.5\% of RoboTwin queries, cutting latency by 38\% while improving average success to 93.3\% on RoboTwin~2.0 and 98.9\% on LIBERO. On physical bimanual manipulation across three real-world tasks, Utility-WAM succeeds in 53 of 60 trials, compared to 43 for FAST-WAM.
We introduce DeepInterestGR, a novel framework that integrates deep interest mining into the generative recommendation pipeline. This addresses the "Shallow Interest" problem: existing generative methods rely on surface-level textual features and fail to capture latent user motivations, limiting personalization depth and recommendation interpretability. Our approach leverages Multi-LLM Interest Mining (MLIM) via structured reasoning prompting, Reward-Labeled Deep Interest (RLDI) for quality control, and Interest-Enhanced Item Discretization (IEID) via RQ-VAE, combined with a two-stage SFT-GRPO training pipeline guided by an Interest-Aware Reward. We validate DeepInterestGR on three Amazon Review benchmarks (Beauty, Sports, Instruments), comparing against 14 state-of-the-art baselines including SASRec, BERT4Rec, TIGER, LC-Rec, and S-DPO. Our method achieves 12.4%-15.4% relative improvements on HR@10 and 15.5%-17.9% on NDCG@10, with cross-domain generalization gains of +24.8%. To our knowledge, this is the first work to demonstrate such significant gains by incorporating deep semantic interests into generative recommendation.
Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.
Ruoyu Wang, Xinyi Ye, Yunshuo Shi, Liangyu Yuan, Beier Zhu, Chi Zhang
We present a variational control framework that connects sampling-time guidance and reward-based model adaptation through a shared Jacobian pullback. Starting from terminal reward maximization with a path-space KL penalty, the Gibbs variational principle and Doob transform yield a correction to the generative dynamics. A local denoising approximation exposes the pullback that transports output preferences to the controlled variable. This construction gives Variational Optimal Guidance (VOG) in state space and extends to Distilled Variational Optimal Control (DVOC) by amortizing locally improved endpoints into model parameters. The resulting controls share a local variational rule: VOG acts through the denoising Jacobian, while DVOC realizes the parameter pullback by endpoint distillation. Under a linear MMSE model, VOG's exact correction lies in the data subspace. On ImageNet, VOG reduces DiT-XL/2 FID from 2.27 to 2.04 at 250 sampling steps and from 7.58 to 4.44 at 25 steps. After 20 updates on Z-Image-Turbo, DVOC improves HPSv3++ and four held-out evaluator scores over the untrained model, with the highest corresponding means among the trained methods compared. These results connect inference-time control and reward adaptation through a common geometric principle.
Hoyoung Lee, Suyeol Yun, Jack Haverty, Yunju Cho, Meesong Kim, Daekyung Park, Sumin Kim, Jihoon Kwon 等 20 位作者
Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every agent, as prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizon loops that follow the expert guidance, a writer agent researches every expected value and a reviewer agent verifies it, and failures escalate to a human. On three expert-authored finance benchmarks, its rubrics track expert scoring as closely as the strongest evaluated generator while stating the expert rubric's expected value for more criteria, their scores agree with human grading, and in-house analysts prefer them in a blind review. The released 100-query FinAutoRubric Benchmark, built from in-house analysts' key questions across 78 tasks and eight asset classes, shows that rubrics from an earlier model generation still leave headroom for a later one.
Shitong Liu, Jingwei Zhang, Sheng Lian, Xinyu Zhuang, Kaiwen Guo, Quan Liu, Chunhai Zhao, Jiaxin He 等 20 位作者
Realizing Embodied AI for Science requires robots to translate experimental goals into reliable physical procedures, reducing hazardous and repetitive human work while generating evidence for scientific discovery. Although language-based planning and learned manipulation provide complementary capabilities, their integration requires robots to adapt subsequent operations to actual execution outcomes. For example, an unsuccessful placement changes what must be done next, even when the experimental goal remains unchanged. Existing benchmarks assess planning, manipulation, and laboratory workflows through task completion and reasoning or execution metrics; however, aggregate performance leaves the connection between outcome-dependent choices and physical execution unresolved. To address this evaluation gap, we introduce Labference, a benchmark for evaluating how observed physical outcomes guide subsequent choices and how those choices translate into robotic laboratory actions. Its evaluation protocol is designed to test outcome-dependent behavioral adaptation through controlled evidence variations, while independently measuring operation selection, physical execution, and task completion. Matched Oracle-assisted continuations from shared checkpoints then assess which forms of support improve subsequent choices and task completion. Initial weighing evaluations reveal target-selection errors in the tested VLA policies despite successful object transfers, whereas GPT-driven control achieves correct selection but encounters execution failures and substantial computation costs. Together, these findings highlight the need to connect task-appropriate reasoning with reliable, timely action. By making this connection measurable and diagnosable, Labference supports targeted improvements toward autonomous experimentation for Embodied AI for Science.
Physical reasoning underpins how embodied systems understand and act in the physical world, yet vision-language models (VLMs) remain unreliable on questions about dynamics and physical causality. Progress is critically constrained by the scarcity of grounded counterfactual training data, as observational videos capture only the factual trajectory that occurred. The self-evolving paradigm offers a route beyond fixed datasets by enabling models to construct their own training problems. Extending this paradigm to physics, however, requires an external source of truth that can both validate model-proposed environments and verify alternative physical outcomes under intervention. We introduce \physevolve{}, a verifier-grounded self-evolving framework that trains VLMs for causal physical reasoning from model-proposed executable worlds and simulation-authored tasks. At each round, a shared VLM proposes executable world programs and evidence schemas; a deterministic physics engine freezes each valid world, simulates matched baseline and body-elided counterfactual branches, and synthesizes discrete, answer-bound visual tasks. Exact verifier feedback from task solving updates both the shared policy via GRPO and an adaptive curriculum over physical intents. Starting from Qwen3-VL-8B-Instruct, \physevolve{} achieves targeted gains across PhysBench, CausalPhys, and ContPhy without human intervention data, improving PhysBench Throwing by $8.8$ points and ContPhy Counterfactual Removal and Goal-Pit by $7.4$ and $24.4$ points. These gains concentrate on interaction-sensitive and altered-world questions, demonstrating zero-shot transfer of causal principles to unseen complex dynamics (cloth, fluid, soft bodies) and real-world video.
Zhengyi Li, Yakai Wang, Jingwen Leng Shanghai Jiao Tong University, Kang Yang, Yu Yu, Jiaping Gui Shanghai Jiao Tong University, Yu Feng Shanghai Jiaotong University, Ning Liu 等 9 位作者
For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client’s input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works reveal intermediate activations to the client, allowing nonlinear operations to be computed in plaintext. Although this approach significantly improves efficiency, exposing activations enables adversaries to extract model weights. To mitigate this risk, existing works employ a shuffling defense that reveals only randomly permuted activations to the client. In this work, we show that the shuffling defense is not as robust as previously claimed. We propose an attack that aligns differently shuffled activations to a common permutation and subsequently exploits them to extract model weights. Experiments on Pythia-70m and GPT-2 demonstrate that the proposed attack can align shuffled activations with mean squared errors ranging from 10^{-9} to 10^{-6}. With a query cost of approximately $1, the adversary can recover model weights with L1-norm differences ranging from 10^{-4} to 10^{-2} compared to the oracle weights.
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
Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang Stanford University, Jiaming Han, Benyou Wang The Chinese University of Hong Kong, Shenzhen 等 11 位作者
Recent multimodal large language models (MLLMs), such as GPT-4o, Gemini 1.5/2.5 Pro, and Reka Core, have advanced audio-visual reasoning capabilities, achieving strong performance in tasks like cross-modal understanding and generation. However, our DeafTest uncovers unanticipated failures: most of the state-of-the-art MLLMs struggle with very simple audio tasks, such as distinguishing louder sounds or sound counting. This raises a fundamental question—does a deficiency in low-level audio perception constrain higher-level audio-visual reasoning? To address this, we introduce AV-Odyssey Bench—a comprehensive benchmark of 4,555 meticulously designed problems that integrate text, audio, and visual modalities. Each task requires models to unify cross-modal reasoning, leveraging synchronized audio-visual cues to infer solutions. By structuring questions as multiple-choice, we ensure objective, reproducible evaluations without reliance on subjective human or LLM-based judgments. Through comprehensive benchmarking of closed-source and open-source models, we showcase: (i) current MLLMs lack robust audio-visual integration ability and (ii) performance on DeafTest (Pearson’s r = 0.945) strongly correlates with AV-Odyssey accuracy. These findings challenge assumptions about models’ multimodal proficiency and highlight fundamental audio perception as a reasoning bottleneck. We believe that our results provide concrete guidance for future dataset design, alignment strategies, and architectures.
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
Lung-Hao Lee National Yang Ming Chiao Tung University, Liang-Chih Yu Yuan Ze University, Natalia V Loukachevitch, Ilseyar Alimova Kazan Federal University, Alexander Panchenko S-NLP group, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou National Yang Ming Chiao Tung University 等 16 位作者
Aspect-Based Sentiment Analysis (ABSA) focuses on extracting sentiment at a fine-grained aspect level and has been widely applied across real-world domains. However, existing ABSA research relies on coarse-grained categorical labels (e.g., positive, negative), which limits its ability to capture nuanced affective states. To address this limitation, we adopt a dimensional approach that represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. To this end, we introduce DimABSA, the first multilingual, dimensional ABSA resource annotated with both traditional ABSA elements (aspect terms, aspect categories, and opinion terms) and newly introduced VA scores. This resource contains 76,958 aspect instances across 42,590 sentences, spanning six languages and four domains. We further introduce three subtasks that combine VA scores with different ABSA elements, providing a bridge from traditional ABSA to dimensional ABSA. Given that these subtasks involve both categorical and continuous outputs, we propose a new unified metric, continuous F1 (cF1), which incorporates VA prediction error into standard F1. We provide a comprehensive benchmark using both prompted and fine-tuned large language models across all subtasks. Our results show that DimABSA is a challenging benchmark and provides a foundation for advancing multilingual dimensional ABSA. We publicly released the DimABSA dataset, which was used for Track A of SemEval-2026 Task 3, attracting over 300 participants.
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
Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng Large Model Data Technology Lab, Huawei Technologies Ltd., Jiansheng Wei, Jiaqing Liang Fudan University, Yanghua Xiao Fudan University
Metaphor reasoning is an essential cognitive ability that maps knowledge from familiar domains to more abstract domains. This ability functions as a meta-ability underlying many types of reasoning. However, existing work rarely investigates how metaphor reasoning affects other reasoning abilities. To bridge this gap, we systematically study how metaphor reasoning, particularly through metaphorical riddles, can enhance broader reasoning abilities in large language models. We propose MetaR, an automated system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable. Leveraging that answer categories determine riddle categories, we employ a hierarchical answer taxonomy for the former three criteria and a multi-agent refinement framework for the latter two, generating a high-quality dataset. Training with reinforcement learning on verifiable rewards using only thousands of metaphorical riddles, we demonstrate improvements across six out-of-distribution reasoning domains. Analysis reveals transfer effectiveness depends on model scale and pattern-target domain alignment. The datasets and code are publicly available at https://github.com/Abbey4799/MetaR.
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 1: Long Papers) · 2026 · 正式发表
Wei Zhu, Jian Zhang, Lixing Yu Yunnan University, Kun Yue Yunnan University, Zhiwen Tang Yunnan University
Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect. These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions. Based on these observations, we introduce GUARD, a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals. Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes. Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.
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
Tianhong Gao, Jundong Shen ByteDance Inc., Jiapeng Wang, Bei Shi ByteDance Inc., Ying Ju, Junfeng Yao, Huiyu Yu
Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements, overemphasizing verifiable task success while under-measuring subjective service quality and realistic failure modes, leaving a gap between offline gains and deployable dialogue behavior. We close this gap with a benchmark-to-optimization loop: we first introduce OlaBench, an ICS benchmark spanning retrieval-augmented generation, workflow-based systems, and agentic settings, which evaluates service capability, safety, and latency sensitivity; moreover, motivated by OlaBench results showing state-of-the-art LLMs still fall short, we propose OlaMind, which distills reusable reasoning patterns and service strategies from expert dialogues and applies staged exploration–exploitation reinforcement learning with instance-level rubric-aware guidance to improve model capability. OlaMind surpasses GPT-5.2 and Gemini 3 Pro on OlaBench (83.64 vs. 70.58/70.84) and, in online A/B tests, delivers an average +23.67% issue resolution and -6.6% human transfer rate versus the baseline, bridging offline gains to deployment. Together, OlaBench and OlaMind advance ICS systems toward more anthropomorphic, professional, and reliable deployment. The project page and evaluation are available at https://olamind-olabench.github.io.
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
Hao Wang, Hao Gu The Hong Kong University of Science and Technology, Hongming Piao City University of Hong Kong, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue The Chinese University of Hong Kong, Sirui Han The Hong Kong University of Science and Technology, Yike Guo Hong Kong University of Science and Technology and Imperial College London 等 9 位作者
The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore. Adding entropy regularization during SFT is not a cure-all; it tends to flatten token distributions toward uniformity, increasing entropy without improving meaningful exploration capability. In this paper, we propose CurioSFT, an entropy-preserving SFT method designed to enhance exploration capabilities through intrinsic curiosity. It consists of (a) Self-Exploratory Distillation, which distills the model toward a self-generated, temperature-scaled teacher to encourage exploration within its capability; and (b) Entropy-Guided Temperature Selection, which adaptively adjusts distillation strength to mitigate knowledge forgetting by amplifying exploration at reasoning tokens while stabilizing factual tokens. Extensive experiments on mathematical reasoning tasks demonstrate that, in SFT stage, CurioSFT outperforms the vanilla SFT by 2.5 points on in-distribution tasks and 2.9 points on out-of-distribution tasks. We also verify that exploration capabilities preserved during SFT successfully translate into concrete gains in RL stage, yielding an average improvement of 5.0 points. Code is available at https://github.com/HaoooWang/CurioSFT.
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
George Ma University of California, Berkeley, Anurag Koul Amazon, Qi Chen Amazon, Yawen Wu Amazon, Sachit Kuhar Amazon, Yu Yu Hark and Amazon, Aritra Sengupta Amazon, Varun Kumar Amazon 等 9 位作者
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. Low inference time latency budget either affects retrieval quality or the added latency impacts user experience adversely. We address this limitation with SpecAgent, an agent that enhances both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context that anticipates future edits in each file. This indexing-time asynchrony allows thorough context computation masking latency and the speculative nature of the context improves code-generation quality. Additionally, we identify the problem of future context leakage in existing benchmarks, which can inflate reported performance. To address this, we construct a synthetic, leakage-free benchmark that enables a more realistic evaluation of our agent against baselines. Experiments show that SpecAgent consistently achieves absolute gains of 9–11% (48–58% relative) compared to the best-performing baselines, while significantly reducing inference latency.
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
Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu Tianjin University, Xiaomian Kang Institute of automation, Chinese academy of science, Delai Qiu, Fa Zhang, Genpeng Zhen 等 13 位作者
Reading order detection is the foundation of document understanding.Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: Positional Disparity, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections.This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts.To address this, we propose FocalOrder, a framework driven by Focal Preference Optimization (FPO).Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while introducing a difficulty-calibrated pairwise ranking objective to enforce global logical consistency.Extensive experiments demonstrate that FocalOrder establishes new state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc.Our compact model not only outperforms competitive specialized baselines but also significantly surpasses large-scale general VLMs.These results demonstrate that aligning the optimization with intrinsic structural ambiguity of documents is critical for mastering complex document structures.
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
Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure cases, but the optimization process remains black-box and label-free, leading to uninterpretable trajectories and systematic failure. We identify and empirically demonstrate four limitations: on GSM8K with a defective seed, GEPA degrades accuracy from 23.81% to 13.50%. We propose VISTA, a multi-agent APO framework that decouples hypothesis generation from prompt rewriting, enabling semantically labeled hypotheses, parallel minibatch verification, and interpretable optimization trace. A two-layer explore-exploit mechanism combining random restart and epsilon-greedy sampling further escapes local optima. VISTA recovers accuracy to 87.57% on the same defective seed and consistently outperforms baselines across all conditions on GSM8K and AIME2025.
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 4: Student Research Workshop) · 2026 · 正式发表