Predicting the complexity of source code is essential for software development and algorithm analysis. Recently, Baik et al. (2025) introduced CodeComplex for code time complexity prediction. The paper shows that LLMs without fine-tuning struggle with certain complexity classes. This suggests that no single LLM excels at every class, but rather each model shows advantages in certain classes. We propose MEC$^3$O, a multi-expert consensus system, which extends the multi-agent debate frameworks. MEC$^3$O assigns LLMs to complexity classes based on their performance and provides them with class-specialized instructions, turning them into experts. These experts engage in structured debates, and their predictions are integrated through a weighted consensus mechanism. Our expertise assignments to LLMs effectively handle Degeneration-of-Thought, reducing reliance on a separate judge model, and preventing convergence to incorrect majority opinions. Experiments on CodeComplex show that MEC$^3$O outperforms the open-source baselines, achieving at least 10% higher accuracy and macro-F1 scores. It also surpasses GPT-4o-mini in macro-F1 scores on average and demonstrates competitive on-par F1 scores to GPT-4o and GPT-o4-mini on average. This demonstrates the effectiveness of multi-expert debates and weight consensus strategy to generate the final predictions. Our code and data is available at https://github.com/suhanmen/MECO.

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study adaptive attacks by an untrusted model that knows the protocol and the monitor model, which is plausible if the untrusted model was trained with a later knowledge cutoff or can search for this information autonomously. We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs. Using this tactic, frontier models consistently evade diverse monitors and complete malicious tasks on two main AI control benchmarks. The attack works universally against current protocols that rely on a monitor. Furthermore, the recent Defer-to-Resample protocol even backfires, as its resampling amplifies the prompt injection and effectively reframes it as a best-of-$n$ attack. In general, adaptive attacks on monitor models represent a major blind spot in current control protocols and should become a standard component of evaluations for future AI control mechanisms.

Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, training-free prompting strategy to circumvent mode collapse. VS prompts the model to verbalize a probability distribution over a set of responses (e.g., "Generate 5 jokes about coffee and their corresponding probabilities"). Comprehensive experiments show that VS significantly improves performance across creative writing (poems, stories, jokes), dialogue simulation, open-ended QA, and synthetic data generation, without sacrificing factual accuracy and safety. For instance, in creative writing, VS increases diversity by 1.6-2.1x over direct prompting. We further observe an emergent trend that more capable models benefit more from VS. In sum, our work provides a new data-centric perspective on mode collapse and a practical inference-time remedy that helps unlock pre-trained generative diversity.

Cricket shot classification from video sequences remains a challenging problem in sports video analysis, requiring effective modeling of both spatial and temporal features. This paper presents the first comprehensive baseline study comparing seven different deep learning approaches across four distinct research paradigms for cricket shot classification. We implement and systematically evaluate traditional CNN-LSTM architectures, attention-based models, vision transformers, transfer learning approaches, and modern EfficientNet-GRU combinations on a unified benchmark. A critical finding of our study is the significant performance gap between claims in academic literature and practical implementation results. While previous papers reported accuracies of 96\% (Balaji LRCN), 99.2\% (IJERCSE), and 93\% (Sensors), our standardized re-implementations achieve 46.0\%, 55.6\%, and 57.7\% respectively. Our modern SOTA approach, combining EfficientNet-B0 with a GRU-based temporal model, achieves 92.25\% accuracy, demonstrating that substantial improvements are possible with modern architectures and systematic optimization. All implementations follow modern MLOps practices with PyTorch Lightning, providing a reproducible research platform that exposes the critical importance of standardized evaluation protocols in sports video analysis research.

Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strategy selection, overlooking the significance of persuasive communication in influencing other players' beliefs and responses. In SDGs, success depends not only on making correct deductions but on convincing others to response in alignment with one's intent. To address this limitation, we formalize turn-based dialogue in SDGs as a Stackelberg competition, where the current player acts as the leader who strategically influences the follower's response. Building on this theoretical foundation, we propose a reinforcement learning framework that trains agents to optimize utterances for persuasive impact. Through comprehensive experiments across three diverse SDGs, we demonstrate that our agents significantly outperform baselines. This work represents a significant step toward developing AI agents capable of strategic social influence, with implications extending to scenarios requiring persuasive communication.

Music learners can greatly benefit from tools that accurately detect errors in their practice. Existing approaches typically compare audio recordings to music scores using heuristics or learnable models. This paper introduces \textit{LadderSym}, a novel Transformer-based method for music error detection. \textit{LadderSym} is guided by two key observations about the state-of-the-art approaches: (1) late fusion limits inter-stream alignment and cross-modality comparison capability; and (2) reliance on score audio introduces ambiguity in the frequency spectrum, degrading performance in music with concurrent notes. To address these limitations, \textit{LadderSym} introduces (1) a two-stream encoder with inter-stream alignment modules to improve audio comparison capabilities and error detection F1 scores, and (2) a multimodal strategy that leverages both audio and symbolic scores by incorporating symbolic representations as decoder prompts, reducing ambiguity and improving F1 scores. We evaluate our method on the \textit{MAESTRO-E} and \textit{CocoChorales-E} datasets by measuring the F1 score for each note category. Compared to the previous state of the art, \textit{LadderSym} more than doubles F1 for missed notes on \textit{MAESTRO-E} (26.8\% $\rightarrow$ 56.3\%) and improves extra note detection by 14.4 points (72.0\% $\rightarrow$ 86.4\%). Similar gains are observed on \textit{CocoChorales-E}. This work introduces general insights about comparison models that could inform sequence evaluation tasks for reinforcement Learning, human skill assessment, and model evaluation.

To address the dual challenges of inherent stochasticity and non-differentiable metrics in physical spatiotemporal forecasting, we propose Spatiotemporal Forecasting as Planning (SFP), a new paradigm grounded in Model-Based Reinforcement Learning. SFP constructs a novel Generative World Model to simulate diverse, high-fidelity future states, enabling an "imagination-based" environmental simulation. Within this framework, a base forecasting model acts as an agent, guided by a beam search-based planning algorithm that leverages non-differentiable domain metrics as reward signals to explore high-return future sequences. These identified high-reward candidates then serve as pseudo-labels to continuously optimize the agent's policy through iterative self-training, significantly reducing prediction error and demonstrating exceptional performance on critical domain metrics like capturing extreme events.

The use of derogatory terms in languages that employ code mixing, such as Roman Urdu, presents challenges for Natural Language Processing systems due to unstated grammar, inconsistent spelling, and a scarcity of labeled data. In this work, we propose a QLoRA based fine tuning framework to improve offensive language detection in Roman Urdu-English text. We translated the Roman Urdu-English code mixed dataset into English using Google Translate to leverage English LLMs, while acknowledging that this translation reduces direct engagement with code mixing features. Our focus is on classification performance using English translated low resource inputs. We fine tuned several transformers and large language models, including Meta LLaMA 3 8B, Mistral 7B v0.1, LLaMA 2 7B, ModernBERT, and RoBERTa, with QLoRA for memory efficient adaptation. Models were trained and evaluated on a manually annotated Roman Urdu dataset for offensive vs non offensive content. Of all tested models, the highest F1 score of 91.45 was attained by Meta LLaMA 3 8B, followed by Mistral 7B at 89.66, surpassing traditional transformer baselines. These results demonstrate the efficacy of QLoRA in fine tuning high performing models for low resource environments such as code mixed offensive language detection, and confirm the potential of LLMs for this task. This work advances a scalable approach to Roman Urdu moderation and paves the way for future multilingual offensive detection systems based on LLMs.

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably contain imprecise information in conditional inputs. Such supervision, often stemming from noisy, ambiguous, or incomplete labels, will cause condition mismatch and degrade generation quality. To address this challenge, we propose DMIS, a unified framework for training robust Diffusion Models from Imprecise Supervision, which is the first systematic study within diffusion models. Our framework is derived from likelihood maximization and decomposes the objective into generative and classification components: the generative component models imprecise-label distributions, while the classification component leverages a diffusion classifier to infer class-posterior probabilities, with its efficiency further improved by an optimized timestep sampling strategy. Extensive experiments on diverse forms of imprecise supervision, covering tasks of image generation, weakly supervised learning, and noisy dataset condensation demonstrate that DMIS consistently produces high-quality and class-discriminative samples.

Large language models (LLMs) excel at knowledge-intensive question answering and reasoning, yet their real-world deployment remains constrained by knowledge cutoff, hallucination, and limited interaction modalities. Augmenting LLMs with external search tools helps alleviate these issues, but it also exposes agents to a complex search environment in which small, plausible variations in query formulation can steer reasoning into unproductive trajectories and amplify errors. We present a systematic analysis that quantifies how environmental complexity induces fragile search behaviors and, in turn, degrades overall performance. To address this challenge, we propose a simple yet effective approach to instantiate a search agent, RE-Searcher. During search, RE-Searcher explicitly articulates a concrete search goal and subsequently reflects on whether the retrieved evidence satisfies that goal. This combination of goal-oriented planning and self-reflection enables RE-Searcher to resist spurious cues in complex search environments and perform robust search. Extensive experiments show that our method improves search accuracy and achieves state-of-the-art results. Perturbation studies further demonstrate substantial resilience to noisy or misleading external signals, mitigating the fragility of the search process. We believe these findings offer practical guidance for integrating LLM-powered agents into more complex interactive environments and enabling more autonomous decision-making.