January 2026

arXiv:2601.15333v1 Announce Type: new Abstract: Large Language Models (LLMs) possess strong representation and reasoning capabilities, but their application to structure-based drug design (SBDD) is limited by insufficient understanding of protein structures and unpredictable molecular generation. To address these challenges, we propose Exploration-Augmented Latent Inference for LLMs (ELILLM), a framework that reinterprets the LLM generation process as an encoding, latent space exploration, and decoding workflow. ELILLM explicitly explores portions of the design problem beyond the model’s current knowledge while […]

Ver mais

arXiv:2601.15331v1 Announce Type: new Abstract: The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This […]

Ver mais

arXiv:2601.15330v1 Announce Type: new Abstract: Large Language Models (LLMs) in multi-turn conversations often suffer from a “lost-in-conversation” phenomenon, where they struggle to recover from early incorrect assumptions, particularly when users provide ambiguous initial instructions. We find that standard post-training techniques like Reinforcement Learning with Verifiable Rewards (RLVR) exacerbate this issue by rewarding confident, direct answers, thereby inducing overconfidence and discouraging the model from seeking clarification. To address this, we propose Illocution-Calibrated Policy Optimization (ICPO), a novel training framework […]

Ver mais

arXiv:2601.15327v1 Announce Type: new Abstract: In many competitive settings, from education to politics, rules do not reward effort evenly, and thresholds (e.g., grade cutoffs or electoral majorities) make some moments disproportionately important. Success thus depends on efficiently allocating limited resources. However, empirical demonstration has been difficult because effort allocation is rarely observable and feedback is often delayed, limiting our understanding of expertise. Professional tennis provides an ideal natural experiment. Because each game resets after a player wins four […]

Ver mais

arXiv:2601.15325v1 Announce Type: new Abstract: Dynamic community detection plays a crucial role in understanding the temporal evolution of community structures in complex networks. Existing methods based on nonnegative tensor RESCAL decomposition typically require the decomposition rank to equal the number of communities, which limits model flexibility. This paper proposes an improved MLP-enhanced nonnegative tensor decomposition model (MLP-NTD) that incorporates a multilayer perceptron (MLP) after RESCAL decomposition for community mapping, thereby decoupling the decomposition rank from the number of […]

Ver mais

arXiv:2601.15324v1 Announce Type: new Abstract: Adding memory to pretrained language models typically requires architectural changes or weight modification. We present Prometheus Mind, which retrofits memory to a frozen Qwen3-4B using 11 modular adapters (530MB, 7% overhead) — fully reversible by removing the adapters. Building this system required solving four problems: (1) Extraction — we develop Contrastive Direction Discovery (CDD), which finds semantic directions via minimal pairs without labeled data. (2) Training — end-to-end optimization collapses; stage-wise training of […]

Ver mais

arXiv:2601.15322v1 Announce Type: new Abstract: LLM agents struggle with regulatory audit replay: when asked to reproduce a flagged transaction decision with identical inputs, most deployments fail to return consistent results. This paper introduces the Determinism-Faithfulness Assurance Harness (DFAH), a framework for measuring trajectory determinism and evidence-conditioned faithfulness in tool-using agents deployed in financial services. Across 74 configurations (12 models, 4 providers, 8-24 runs each at T=0.0) in non-agentic baseline experiments, 7-20B parameter models achieved 100% determinism, while 120B+ […]

Ver mais

arXiv:2601.15318v1 Announce Type: new Abstract: Cooperative games with nonempty core are called balanced, and the set of balanced games is a polyhedron. Given a game with empty core, we look for the closest balanced game, in the sense of the (weighted) Euclidean distance, i.e., the orthogonal projection of the game on the set of balanced games. Besides an analytical approach which becomes rapidly intractable, we propose a fast algorithm to find the closest balanced game, avoiding exponential complexity […]

Ver mais

arXiv:2601.15316v1 Announce Type: new Abstract: In recent years, the rapid evolution of large vision-language models (LVLMs) has driven a paradigm shift in multimodal fake news detection (MFND), transforming it from traditional feature-engineering approaches to unified, end-to-end multimodal reasoning frameworks. Early methods primarily relied on shallow fusion techniques to capture correlations between text and images, but they struggled with high-level semantic understanding and complex cross-modal interactions. The emergence of LVLMs has fundamentally changed this landscape by enabling joint modeling […]

Ver mais

arXiv:2601.15312v1 Announce Type: new Abstract: While delegating tasks to large language models (LLMs) can save people time, there is growing evidence that offloading tasks to such models produces social costs. We use behavior in two canonical economic games to study whether people have different expectations when decisions are made by LLMs acting on their behalf instead of themselves. More specifically, we study the social appropriateness of a spectrum of possible behaviors: when LLMs divide resources on our behalf […]

Ver mais