Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers

A human-like chess engine should mimic the style, errors, and consistency of a strong human player rather than maximize playing strength. We show that training from move sequences alone forces a model to learn two capabilities: state tracking, which reconstructs the board from move history, and decision quality, which selects good moves from that reconstructed state. These impose contradictory data requirements: low-rated games provide the diversity needed for tracking, while high-rated games provide the quality signal for decision learning. Removing low-rated data degrades performance. We formalize this tension as a dual-capability bottleneck, P <= min(T,Q), where overall performance is limited by the weaker capability. Guided by this view, we scale the model from 28M to 120M parameters to improve tracking, then introduce Elo-weighted training to improve decisions while preserving diversity. A 2 x 2 factorial ablation shows that scaling improves tracking, weighting improves decisions, and their combination is superadditive. Linear weighting works best, while overly aggressive weighting harms tracking despite lower validation loss. We also introduce a coverage-decay formula, t* = log(N/kcrit)/log b, as a reliability horizon for intra-game degeneration risk. Our final 120M-parameter model, without search, reached Lichess bullet 2570 over 253 rated games. On human move prediction it achieves 55.2% Top-1 accuracy, exceeding Maia-2 rapid and Maia-2 blitz. Unlike position-based methods, sequence input naturally encodes full game history, enabling history-dependent decisions that single-position models cannot exhibit.

CRED: Counterfactual Reasoning and Environment Design for Active Preference Learning

As a robot's operational environment and tasks to perform within it grow in complexity, the explicit specification and balancing of optimization objectives to achieve a preferred behavior profile moves increasingly farther out of reach. These systems benefit strongly by being able to align their behavior to reflect human preferences and respond to corrections, but manually encoding this feedback is infeasible. Active preference learning (APL) learns human reward functions by presenting trajectories for ranking. However, existing methods sample from fixed trajectory sets or replay buffers that limit query diversity and often fail to identify informative comparisons. We propose CRED, a novel trajectory generation method for APL that improves reward inference by jointly optimizing environment design and trajectory selection to efficiently query and extract preferences from users. CRED "imagines" new scenarios through environment design and leverages counterfactual reasoning -- by sampling possible rewards from its current belief and asking "What if this were the true preference?" -- to generate trajectory pairs that expose differences between competing reward functions. Comprehensive experiments and a user study show that CRED significantly outperforms state-of-the-art methods in reward accuracy and sample efficiency and receives higher user ratings.

SecAgent: Efficient Mobile GUI Agent with Semantic Context

Mobile Graphical User Interface (GUI) agents powered by multimodal large language models have demonstrated promising capabilities in automating complex smartphone tasks. However, existing approaches face two critical limitations: the scarcity of high-quality multilingual datasets, particularly for non-English ecosystems, and inefficient history representation methods. To address these challenges, we present SecAgent, an efficient mobile GUI agent at 3B scale. We first construct a human-verified Chinese mobile GUI dataset with 18k grounding samples and 121k navigation steps across 44 applications, along with a Chinese navigation benchmark featuring multi-choice action annotations. Building upon this dataset, we propose a semantic context mechanism that distills history screenshots and actions into concise, natural language summaries, significantly reducing computational costs while preserving task-relevant information. Through supervised and reinforcement fine-tuning, SecAgent outperforms similar-scale baselines and achieves performance comparable to 7B-8B models on our and public navigation benchmarks. We will open-source the training dataset, benchmark, model, and code to advance research in multilingual mobile GUI automation.

Adaptive Memory Admission Control for LLM Agents

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversational content, including hallucinated or obsolete facts, or depend on opaque, fully LLM-driven memory policies that are costly and difficult to audit. As a result, memory admission remains a poorly specified and weakly controlled component in agent architectures. To address this gap, we propose Adaptive Memory Admission Control (A-MAC), a framework that treats memory admission as a structured decision problem. A-MAC decomposes memory value into five complementary and interpretable factors: future utility, factual confidence, semantic novelty, temporal recency, and content type prior. The framework combines lightweight rule-based feature extraction with a single LLM-assisted utility assessment, and learns domain-adaptive admission policies through cross-validated optimization. This design enables transparent and efficient control over long-term memory. Experiments on the LoCoMo benchmark show that A-MAC achieves a superior precision-recall tradeoff, improving F1 to 0.583 while reducing latency by 31% compared to state-of-the-art LLM-native memory systems. Ablation results identify content type prior as the most influential factor for reliable memory admission. These findings demonstrate that explicit and interpretable admission control is a critical design principle for scalable and reliable memory in LLM-based agents.

Distributed vs. Centralized Precoding in Cell-Free Systems: Impact of Realistic Per-AP Power Limits

In cell-free massive MIMO, centralized precoding is {theoretically known} to {remarkably} outperform its distributed counterparts, albeit {with} high implementation complexity. However, this letter highlights a practical limitation {often overlooked:} {widely used closed-form} centralized {precoders} are typically derived under a sum-power constraint, which often demands unrealistic power allocation that exceeds hardware capabilities. {When two simple heuristics (global power scaling and local normalization) are applied to enforce the per-AP instantaneous power constraint}, the centralized performance superiority disappears, making distributed precoding {a robust option}.

Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling

Vision-language models (VLMs) have been proven effective for detecting multi-modal misinformation on social platforms, especially in zero-shot settings with unavailable or delayed annotations. However, a single VLM's capacity falls short in the more complex mixed-source multi-modal misinformation detection (M3D) task. Taking captioned images as an example, in M3D, false information can originate from untruthful texts, forged images, or mismatches between the two modalities. Although recent agentic systems can handle zero-shot M3D by connecting modality-specific VLM agents, their effectiveness is still bottlenecked by their architecture. In existing agentic M3D solutions, for any input sample, each agent performs only one forward reasoning pass, making decisions prone to model randomness and reasoning errors in challenging cases. Moreover, the lack of exploration over alternative reasoning paths prevents modern VLMs from fully utilizing their reasoning capacity. In this work, we present AgentM3D, a multi-agent framework for zero-shot M3D. To amplify the reasoning capability of VLMs, we introduce an adaptive test-time scaling paradigm in which each modality-specific VLM agent applies a Best-of-N mechanism, coupled with a critic agent for task-aligned scoring. The agents are organized in a cascading, modality-specific decision chain to reduce unnecessary computation and limit error propagation. To ensure scalability, a planning agent dynamically determines the maximum number of reasoning paths based on sample difficulty, and an adaptive stopping mechanism prevents excessive reasoning within each agent. Extensive experiments on two M3D benchmarks demonstrate that AgentM3D achieves state-of-the-art zero-shot detection performance compared with various VLM-based and agentic baselines.

Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents

Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved evidence through multi-step reasoning. While promising, existing approaches typically rely on large-scale supervised trajectories or expensive reinforcement learning (RL), leading to high training cost, instability, and a severe cold-start problem for standard VLMs. We propose a training-free paradigm to empower VLMs with autonomous search capabilities via cross-modal model merging. By fusing a text-based search agent with a base VLM, we show that multi-modal search capabilities can be effectively composed without any additional multi-modal training data. To mitigate parameter interference during cross-modal integration, we introduce Optimal Brain Merging (OBM), a saliency-aware merging algorithm that identifies task-critical parameters based on their impact on model loss using only a small set of calibration samples. Extensive experiments on search-intensive benchmarks (e.g., InfoSeek, MMSearch) reveal that: (1) Model merging secures a reasonable performance floor as a zero-shot agent, with OBM achieving superior search rates; (2) OBM significantly raises the performance ceiling as a warm-start strategy, achieving faster convergence and higher peak accuracy than standard VLM initialization.

OMGs: A multi-agent system supporting MDT decision-making across the ovarian tumour care continuum

Ovarian tumour management has increasingly relied on multidisciplinary tumour board (MDT) deliberation to address treatment complexity and disease heterogeneity. However, most patients worldwide lack access to timely expert consensus, particularly in resource-constrained centres where MDT resources are scarce or unavailable. Here we present OMGs (Ovarian tumour Multidisciplinary intelligent aGent System), a multi-agent AI framework where domain-specific agents deliberate collaboratively to integrate multidisciplinary evidence and generate MDT-style recommendations with transparent rationales. To systematically evaluate MDT recommendation quality, we developed SPEAR (Safety, Personalization, Evidence, Actionability, Robustness) and validated OMGs across diverse clinical scenarios spanning the care continuum. In multicentre re-evaluation, OMGs achieved performance comparable to expert MDT consensus ($4.45 \pm 0.30$ versus $4.53 \pm 0.23$), with higher Evidence scores (4.57 versus 3.92). In prospective multicentre evaluation (59 patients), OMGs demonstrated high concordance with routine MDT decisions. Critically, in paired human-AI studies, OMGs most substantially enhanced clinicians' recommendations in Evidence and Robustness, the dimensions most compromised when multidisciplinary expertise is unavailable. These findings suggest that multi-agent deliberative systems can achieve performance comparable to expert MDT consensus, with potential to expand access to specialized oncology expertise in resource-limited settings.

Seeing the Goal, Missing the Truth: Human Accountability for AI Bias

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock returns or earnings) of LLM outputs leads the LLM to generate biased sentiment and competition measures, even though these measures are intended to be downstream task-independent. Goal-aware prompting shifts intermediate measures toward the disclosed downstream objective. This purpose leakage improves performance before the LLM's knowledge cutoff, but with no advantage post-cutoff. AI bias due to "seeing the goal" is not an algorithmic flaw, but stems from human accountability in research design to ensure the statistical validity and reliability of AI-generated measurements.

Analysis of Converged 3D Gaussian Splatting Solutions: Density Effects and Prediction Limit

We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze their statistical properties, revealing stable patterns: mixture-structured scales and bimodal radiance across diverse scenes. To understand what determines these parameters, we apply learnability probes by training predictors to reconstruct RORs from point clouds without rendering supervision. Our analysis uncovers fundamental density-stratification. Dense regions exhibit geometry-correlated parameters amenable to render-free prediction, while sparse regions show systematic failure across architectures. We formalize this through variance decomposition, demonstrating that visibility heterogeneity creates covariance-dominated coupling between geometric and appearance parameters in sparse regions. This reveals the dual character of RORs: geometric primitives where point clouds suffice, and view synthesis primitives where multi-view constraints are essential. We provide density-aware strategies that improve training robustness and discuss architectural implications for systems that adaptively balance feed-forward prediction and rendering-based refinement.