❌

Normal view

Received — 15 September 2026 ⏭

Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yu-Yu Yang · Ti-Rong Wu · Hung Guei · Hsing-Yu Chen · I-Chen Wu
14 September 2026 at 12:00
arXiv:2609.12446v1 Announce Type: new Abstract: Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evaluation benchmark in Werewolf for analyzing communication skills through belief updating. Using LLM-played games, we annotate suspicion and accusation messages and measure how an observing village-side model's beliefs change after each message. We evaluate 40 open-weight LLM configurations on 1,224 annotated messages. Our results show that larger models better distinguish true wolves from villagers based on game history, but accusations still strongly influence their beliefs. Models become more suspicious of the accused target and less suspicious of the accuser, especially when the accuser is trusted, even if the accuser is wolf-aligned. Larger models better resist accusations from accusers they already distrust. Overall, our findings suggest that current open-weight LLMs up to 120B parameters still struggle to integrate accusation content with source trust in strategic communication. Our benchmark and code are available at https://rlg.iis.sinica.edu.tw/papers/werewolf-accusation-benchmark.
Received — 13 September 2026 ⏭

NBR1-Mediated Autophagic Degradation of YTHDF1 Curtails <em>FDX1</em> Translation to Drive Concurrent Multikinase Inhibitor Resistance and Cuproptosis Tolerance

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Weikai Wang · Xin Jiang · Xiaona Chen · Kaiyu Liang · Miaoqin Chen · Kaizhong Lu · Qi Wei · Yuchen Wu · Liyuan Zhu · Yuan Chen · Tianlun Hou · Jingfeng Luo · Chentao Li · Xian Wang · Hongchuan Jin · Lifeng Feng
12 September 2026 at 18:00

Cancer Commun (Lond). 2026 Sep 11;46:0048. doi: 10.34133/cancomm.0048. eCollection 2026.

ABSTRACT

Background: Cancer cells frequently acquire adaptive resistance to targeted therapies; however, strategies capable of concurrently overcoming treatment tolerance and reactivating cell death pathways are currently lacking. Here, we investigated the dual role of ferredoxin 1 (FDX1) in modulating both multikinase inhibitor (MKI) sensitivity and cuproptosis susceptibility in hepatocellular carcinoma (HCC), and sought to develop a therapeutic approach for reversing resistance. Methods: HCC models, both in vitro and in vivo, were employed to investigate the role of FDX1 in MKI resistance and cuproptosis evasion. Polysome profiling, SunTag translation reporters, CRISPR-Cas9 mutagenesis, and mass spectrometry were employed to delineate the underlying mechanisms. A codelivery nanoliposome system was engineered and tested in orthotopic HCC models. Results: Prolonged exposure to MKIs led to the down-regulation of FDX1 protein levels, resulting in MKI resistance and cuproptosis tolerance in HCC both in vitro and in vivo. Mechanistically, we found that MKIs inactivated protein kinase B (PKB, also known as AKT)-mechanistic target of rapamycin (mTOR) signaling, thereby suppressing the SET and MYND domain-containing protein 2 (SMYD2)-mediated methylation of YTH domain family protein 1 (YTHDF1) at lysine 515 (K515). Hypomethylated YTHDF1 was degraded via next to BRCA1 gene 1 protein (NBR1)-dependent autophagy, leading to the repression of N6-methyladenosine modification-dependent translation of FDX1 mRNA. FDX1 deficiency drove MKI resistance by reactivating AKT survival signaling while impairing cuproptosis through reduced divalent copper ions (Cu2+) to monovalent copper ions (Cu+) conversion and the loss of protein lipoylation. Additionally, restoring FDX1 expression through NBR1 knockdown or YTHDF1 overexpression overcame MKI resistance and resensitized HCC cells to cuproptosis. Finally, a nanoliposomal system, super cuproptosis detonator liposome, designed for the codelivery of NBR1 small interfering RNA, a copper ionophore, and sorafenib restored FDX1-dependent cuproptosis and exhibited marked anti-HCC efficacy, suppressing HCC growth in vivo. Conclusions: MKIs suppressed SMYD2-mediated YTHDF1 methylation at K515 via the inactivation of AKT-mTOR signaling. This led to the inhibition of FDX1 translation, resulting in AKT signaling reactivation and protein lipoylation impairment, effects that contributed to both MKI resistance and cuproptosis tolerance in HCC. Overcoming MKI resistance and resensitizing cells to cuproptosis by targeting NBR1-mediated YTHDF1 degradation using a nanoliposomal codelivery system represents a promising strategy for HCC treatment.

PMID:42729649 | PMC:PMC13562797 | DOI:10.34133/cancomm.0048

Received — 10 September 2026 ⏭

A Function-Space Approach to the Statistical Mechanics of Learning Dynamics

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yizhou Zhang · Weichen Wu · Lun Du · Zhengjie Miao
10 September 2026 at 12:00
arXiv:2609.09589v1 Announce Type: new Abstract: Deep neural networks exhibit regular macroscopic behavior despite highly nonlinear dynamics in vast parameter spaces. We develop a statistical-mechanical description of learning directly in function space, treating parameter configurations as microscopic realizations and functions with their dynamical operators as macroscopic variables. For mean-squared loss, the exact error dynamics are governed by the learning operator \(M=JJ^\ast\). Combining the dynamical Boltzmann weight of the conditional stochastic dynamics with the parameter-space density of states, whose local curvature defines a statistical operator \(B\), and integrating over local fluctuations yields $$ \Phi_{\mathrm{fluc}}(M;B)=\frac{\sigma_\xi^2}{2}\log\det(M^{-1}+B)+\mathrm{const}. $$ At fixed spectrum, this term is rotationally stationary when \([M,B]=0\), is minimized by pairing large eigenvalues of \(M\) with small eigenvalues of \(B\), and generates a local restoring contribution against rotational mismatch. For ReLU-type function spaces under mild stable statistical conditions, \(B=\sigma_\xi^2L^\ast\mathcal K L\), where \(L\) measures coarse-grained second-order structure. Thus the low-\(B\) sector corresponds, up to bounded anisotropy of \(\mathcal K\), to low structural curvature, implying a preference for faster relaxation along smooth, data-adaptive directions. These results identify function space as a natural macroscopic level for studying stable collective organization in learning.
Received — 27 May 2026 ⏭

MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games

✇cs.AI, q-bio.NC updates on arXiv.org
By: Qian-Rong Li · Hung Guei · I-Chen Wu · Ti-Rong Wu
26 May 2026 at 12:00
arXiv:2605.24139v1 Announce Type: new Abstract: Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achieved remarkable success in perfect-information games, extending it to IIGs remains difficult. Existing search-based approaches, such as Perfect Information Monte Carlo (PIMC), suffer from strategy fusion, while Information Set Monte Carlo Tree Search (IS-MCTS) incurs high computational cost when combined with neural networks. In this paper, we propose Multi-State Aggregated PoLicy Evaluation (MAPLE), a tree search method that aggregates policy and value evaluations from multiple sampled world states within a single search tree, combining the advantages of PIMC and IS-MCTS while maintaining a controllable computational cost. We further incorporate a Siamese-based sampling strategy to select informative world states from the information set. Experiments on Phantom Go and Dark Hex show that MAPLE significantly outperforms the PIMC-based AlphaZero baseline, achieving Elo improvements of 291 and 136, respectively. These results demonstrate that MAPLE is an effective approach for AlphaZero-style learning in imperfect-information games.

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jingchu Gai · Guanning Zeng · Christina Baek · Chen Wu · J. Zico Kolter · Andrej Risteski · Aditi Raghunathan
26 May 2026 at 12:00
arXiv:2605.24396v1 Announce Type: new Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it.

Pixelated quantum-dot superlattice LEDs

✇Nature - Issue - nature.com science feeds
By: Chengxi Zhang · Qingsen Zeng · Hui Li · Renjun Guo · Yue Yu · Linjie Dai · Lyudmila Turyanska · Zirui Liu · Jun Dai · Yingguo Yang · Yue Zhao · Jun Lu · Lin Wang · Lingmei Kong · Tze Chien Sum · Yuchen Wu · Tae-Woo Lee · Xuyong Yang
15 April 2026 at 08:00

Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10392-z

Scalable fabrication of ordered perovskite quantum dot superlattices enables high-efficiency, ultrahigh-resolution LEDs and active-matrix displays with greatly improved brightness, stability and device lifetime.
Received — 11 March 2026 ⏭

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

✇cs.AI, q-bio.NC updates on arXiv.org
By: Pengcheng Jiang · Jiacheng Lin · Zhiyi Shi · Zifeng Wang · Luxi He · Yichen Wu · Ming Zhong · Peiyang Song · Qizheng Zhang · Heng Wang · Xueqiang Xu · Hanwen Xu · Pengrui Han · Dylan Zhang · Jiashuo Sun · Chaoqi Yang · Kun Qian · Tian Wang · Changran Hu · Manling Li · Quanzheng Li · Hao Peng · Sheng Wang · Jingbo Shang · Chao Zhang · Jiaxuan You · Liyuan Liu · Pan Lu · Yu Zhang · Heng Ji · Yejin Choi · Dawn Song · Jimeng Sun · Jiawei Han
10 March 2026 at 12:00
arXiv:2512.16301v3 Announce Type: replace Abstract: Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.
Received — 5 March 2026 ⏭

MIRAGE: Knowledge Graph-Guided Cross-Cohort MRI Synthesis for Alzheimer's Disease Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Guanchen Wu · Zhe Huang · Yuzhang Xie · Runze Yan · Akul Chopra · Deqiang Qiu · Xiao Hu · Fei Wang · Carl Yang
4 March 2026 at 13:00
arXiv:2603.02434v1 Announce Type: cross Abstract: Reliable Alzheimer's disease (AD) diagnosis increasingly relies on multimodal assessments combining structural Magnetic Resonance Imaging (MRI) and Electronic Health Records (EHR). However, deploying these models is bottlenecked by modality missingness, as MRI scans are expensive and frequently unavailable in many patient cohorts. Furthermore, synthesizing de novo 3D anatomical scans from sparse, high-dimensional tabular records is technically challenging and poses severe clinical risks. To address this, we introduce MIRAGE, a novel framework that reframes the missing-MRI problem as an anatomy-guided cross-modal latent distillation task. First, MIRAGE leverages a Biomedical Knowledge Graph (KG) and Graph Attention Networks to map heterogeneous EHR variables into a unified embedding space that can be propagated from cohorts with real MRIs to cohorts without them. To bridge the semantic gap and enforce physical spatial awareness, we employ a frozen pre-trained 3D U-Net decoder strictly as an auxiliary regularization engine. Supported by a novel cohort-aggregated skip feature compensation strategy, this decoder acts as a rigorous structural penalty, forcing 1D latent representations to encode biologically plausible, macro-level pathological semantics. By exclusively utilizing this distilled "diagnostic-surrogate" representation during inference, MIRAGE completely bypasses computationally expensive 3D voxel reconstruction. Experiments demonstrate that our framework successfully bridges the missing-modality gap, improving the AD classification rate by 13% compared to unimodal baselines in cohorts without real MRIs.
There are no more articles
❌