World Action Planner is a robot planning system that uses an action-conditioned world model to search for and compose executable action plans. The agent performs a coarse-to-fine search: first a global action optimization over imagined rollouts to spot potential failures, then a local action search comparing neighboring candidates to pick the best action. In compositional long-horizon tasks, novel object layouts, and real‑robot planning without expert demonstrations, it consistently outperforms state‑of‑the‑art end‑to‑end generalist policies and VLM planners.
By Xiangcheng Zhang, Runhan Huang, Yilun Du
ProAR introduces a goal‑oriented reasoning framework for autoregressive video models, adding goal‑frame prediction via an asymmetric attention mask and future representation self‑alignment to guide intermediate states. These mechanisms combine sparse target supervision with dense step‑wise guidance, enabling coherent, goal‑directed generation while keeping computational costs modest. Experiments demonstrate consistent performance gains across visual reasoning benchmarks and training efficiency, achieving comparable results to fully trained baselines with only 25% of the training steps.
By Linghui Shen, Tinghui Zhu, Sheng Zhang, Muhao Chen
The paper introduces a hybrid BERT‑CNN‑BiLSTM model for simultaneously classifying Bangla news headlines and performing sentiment analysis. Using the BAN‑ABSA dataset of 9,014 headlines, the authors compare two sampling strategies and report headline accuracy up to 81.37 % and sentiment accuracy up to 73.43 %. The proposed framework outperforms baseline models and establishes new state‑of‑the‑art results for Bangla headline classification and sentiment analysis.
By Mirza Raquib, Munazer Montasir Akash, Tawhid Ahmed, Saydul Akbar Murad, Farida Siddiqi Prity, Mohammad Amzad Hossain, Asif Pervez Polok, Nick Rahimi
The paper introduces KD-Brain, a Prior‑Informed Graph Learning framework that incorporates semantic and clinical priors to model interactions among functional subnetworks in brain networks. It employs a Semantic‑Conditioned Interaction mechanism to guide attention queries by subnetwork identities and a Pathology‑Consistent Constraint to align learned interactions with clinical priors. KD‑Brain achieves state‑of‑the‑art performance on disorder diagnosis tasks and identifies biomarkers that align with psychiatric pathophysiology.
By Siyu Liu, Guangqi Wen, Peng Cao, Jinzhu Yang, Xiaoli Liu, Fei Wang, Osmar R. Zaiane
The paper introduces Harness-Aware Distillation (HAD), a method for training smaller language model agents that preserves the surrounding harness—software managing context, tools, and feedback—while focusing distillation on the teacher’s contributions beyond the harness. HAD combines an action preference that contrasts teacher actions with and without harness information, and a validity check that filters out contradictory preference pairs. Experiments on long-horizon agent benchmarks show that HAD outperforms standard on‑policy distillation, reducing unproductive loops and improving error recovery without requiring task rewards or future information.
By Moonseok Choi, Taehong Moon, Giung Nam, Juho Lee
The paper introduces CoC‑Seduce, a multi‑agent adversarial benchmark for evaluating how well large language models (LLMs) adhere to the rules of the tabletop role‑playing game Call of Cthulhu when acting as adjudicators. Using three LLMs to generate 5,376 samples across diverse settings and skill categories, the study benchmarks 22 target adjudicators and finds that newer releases and explicit reasoning do not guarantee robustness, with pseudo‑logic framing emerging as the most effective manipulation. The benchmark highlights the vulnerability of LLM adjudicators to rhetorical injection attacks that exploit narrative framing to bypass rule enforcement.
By Weiying Chen, Junlong Shen, Zhanyuan Guo, Xiaoou Zhou
The paper introduces PlanPool, a method for agentic Text-to-SQL systems to manage clarification questions by maintaining a mutable question pool. By requiring agents to explicitly ask or drop each planned question, PlanPool improves ambiguity coverage and reduces silent failures compared to unconstrained or prompt-based approaches. Experiments on benchmarks derived from BIRD-Interact and Spider show that PlanPool achieves competitive execution accuracy while better handling underspecification.
By Wen-Zhi Li, Yue Gong, Konstantinos Kanellis, Balakrishnan Murali Narayanaswamy
The paper introduces SafeCut, a method for Source-Free Domain Adaptation that uses Vision‑Language models as external knowledge. SafeCut employs a cut statistic to gauge prediction reliability, enabling a dynamic, reliability‑gated supervision between the source‑pretrained model and the ViL model. This approach selectively amplifies correct mutual corrections while suppressing error propagation, achieving state‑of‑the‑art performance on multiple SFDA benchmarks.
By Seongjun Lee, Changhee Lee
RxnOptBench is a new benchmark that tests large language models on the task of selecting optimal reaction conditions—such as catalyst, ligand, solvent, temperature, and atmosphere—by reading real condition‑screening tables from 2025 organic‑methodology papers. The benchmark uses a continuous relative score that combines yield with stereochemical metrics (ee, dr, rr) and includes a design that separates in‑context literature use from mere memorization. Evaluation across nine frontier LLMs and three chemistry‑specialized LLMs shows that even the best models still have significant room for improvement, with chemistry‑specialized models performing at random levels on multi‑axis selection while open‑weight models approach proprietary models.
By Lingli Ge, Yubin Wang, Junyuan Gao, Jiahe Song, Jiaxing Sun, Boyu Zhu, Haote Yang, Jingchao Wang, Lixin Ma, Jiang Wu, Yuqiang Li, Conghui He
The paper evaluates four main approaches to scalable nonlinear causal discovery—differentiable, amortized, score‑matching, and combinatorial search—highlighting their distinct accuracy‑runtime trade‑offs. It introduces SPADE, a spline‑based score‑evaluation method that compiles and reuses sufficient statistics, reducing combinatorial search complexity from O(nd³) to O(nd²+d³). Empirical results show SPADE dramatically extends the scalability‑accuracy frontier, solving large‑scale problems with high structural accuracy on both synthetic and real‑world data.
By Hendrik Suhr, Sascha Xu, Jilles Vreeken
The paper presents a post‑training approach for text‑to‑image models that combines a preference reward, trained on large human preference data, with rubric‑based rewards that assess prompt faithfulness and other desirable traits. The authors show that a simple reward composition strategy outperforms a naive weighted average, leading to significant Elo gains on the Arena leaderboard for models like Flux2dev and Ideogram‑4. They also release Arena‑T2I‑Training, a 1K subset of data to aid reproducible research in post‑training.
By Yuanhao Ban, I-Hung Hsu, Anastasios Angelopoulos, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh
The paper introduces AdaSpecK, a spectral-Koopman framework designed for Temporal Domain Generalization (TDG). It combines spectral-regularized Koopman dynamics modeling to filter noise in latent space with a context-informed heterogeneous pattern extraction mechanism that uses target-conditioned attention and a learned router to summarize relevant past windows. Experiments on eight classification and regression benchmarks show that AdaSpecK achieves state‑of‑the‑art performance.
By Tengxue Zhang, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, Bin Yang
WebUIProof is a new execution‑oriented benchmark for WebUI code generation that supplies structured specifications and dense, executable interaction tests across general WebUIs and 3D interactive simulations. It employs a UI‑agent harness that runs tests in a headless browser using a plan–act–observe loop to locate DOM elements, perform actions, observe changes, and verify assertions. Evaluations on eight commercial LLMs reveal frequent interaction‑based failures, especially on 3D interfaces, and demonstrate that training compact models with RL rewards from these tests improves functional completion and reduces build failures.
By Yun-Yun Tsai, Yuning Mao, Shiqi Wang, Junfeng Yang, Sinong Wang
The report audits a long‑term‑memory retrieval chain on 500 LongMemEval‑S development questions, evaluating reader performance under an adapted GPT‑4o rubric. Scores vary widely across reader lanes (93–479), with the strongest lanes scoring 479 and 475, and re‑judging the same pass‑1 answers changes three labels, yielding 478. Fixed‑answer knowledge‑update re‑scoring achieves 70/72 or 69/72 depending on the template, and a different‑family reader scores 474, just 1.0 percentage point below the headline pass. The study also reports that live reader request bodies were not retained, that 18 of 23 gains occurred where baseline packets lacked evidence, and that a negative control rejects a verifier that repairs some wrong drafts but breaks many correct ones. Overall, the findings do not establish a new leaderboard leader or a transferable memory advantage, and the released artifacts support packet inspection and re‑scoring but do not reconstruct the method.
By Christopher J. Chanhnourack
The paper introduces GUI agents for continual game generation, presenting PlaytestArena—a benchmark of 200 browser-based game-generation tasks with rubrics for in‑play behavior—and Play2Code, an iterative framework where a game agent and a rubric‑blind GUI playtester refine games through shared memory. Play2Code achieves a 66.8% rubric pass rate, surpassing baseline methods by 37.1 and 14.6 points, and shows consistent score improvement across refinement rounds. The study demonstrates that GUI playtesting provides actionable, traceable feedback that can guide interactive code generation.
By Yixu Huang, Bo Li, Na Li, Zhe Wang, Kaijie Chen, Haonan Ge, Qingyi Si, Yuanzhe Shen, Ruihan Yang, Guangjing Wang, Hongcheng Guo
FastKernels is a benchmark comprising 384 GPU kernel tasks from 47 architectures across 8 categories, designed to evaluate kernel generation agents in realistic production settings. It covers 94.6% of HuggingFace Transformers architectures, scoring kernels on correctness, coverage, and speedup within their native execution paths. The benchmark reveals that kernel‑level speedups often collapse to modest end‑to‑end gains and that isolated performance rankings can misrepresent real‑world effectiveness.
By Gabriele Oliaro, Jaeseong Lee, Yichao Fu, Zhaoyuan Su, Owen Lu, Sreeram Vennam, May Jiang, Junli Wang, Hao Zhang, Zhihao Jia, Samyam Rajbhandari
The paper introduces BenchGuard, a framework that uses advanced language models to audit execution-based agent benchmarks. BenchGuard systematically cross-verifies benchmark artifacts through structured LLM protocols, optionally incorporating agent solutions or execution traces for deeper diagnostics. In tests on ScienceAgentBench and BIXBench Verified-50, BenchGuard uncovered numerous author-confirmed and expert-identified issues, including fatal errors that made tasks unsolvable, and demonstrated cost-effective auditing for complex bioinformatics tasks.
By Xinming Tu (Minta), Tianze Wang (Minta), Yingzhou (Minta), Lu, Kexin Huang, Yuanhao Qu, Sara Mostafavi
Co-Design Gym is a new benchmark suite that enables joint optimization of an agent’s embodiment and its control policy across diverse domains such as robotics, games, and networks. Unlike existing benchmarks that keep the embodiment fixed, this suite includes 20 environment families and over 85 co-design presets, covering tasks from manipulation and locomotion to electricity grids and F1 racing. The authors also provide a systematic evaluation of representative co-design algorithms, outlining the current state of the art.
By Aviraj Newatia, Yordan Tsvetkov, Leonard Pleiss, Andrew Spielberg, Rika Antonova
VisAudit is a new benchmark that tests multimodal agents on visual diagnosis, repair, and verification tasks. It presents agents with rendered charts and auxiliary evidence—such as source data, intended summaries, and code—to iteratively detect defects, modify the visualization, and confirm successful repairs. The benchmark includes 1,900 flawed charts across 21 types and 10 flaw categories, plus 300 correct charts, and shows that current models recover only about 47.4% of flawed charts autonomously.
By Shicheng Liu, Adam Kahirov, Qi Zhang, Zhimin Hu, Song Wang, Junhong Lin, Julian Shun, Yada Zhu
NeuroLens is a self‑supervised model that learns denoised, semantically informative latent embeddings from chronic neural recordings using a Joint‑Embedding Predictive Architecture. It maps changing neural populations into a common latent space and predicts future latent states, thereby reducing sensitivity to transient recording variability. Across chronic intracortical data in mice and humans, NeuroLens improves decoding of decision‑making and semantic task variables, supports multi‑day pretraining, rapid few‑shot adaptation, and yields more stable decoding over time than existing baselines.
By Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie, Anne Churchland, Liam Paninski, Yizi Zhang