arXiv:2605.06420v1 Announce Type: new Abstract: Brain-DNN alignment is usually assessed through stimulus-level correspondence or stimulus-set geometry. Inspired by category theory, we operationalize a different question: do brain and model preserve the same candidate transformations among stimuli? We formalize this as approximate naturality: if a proxy-defined stimulus change is propagated through the brain side and then […]
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
arXiv:2605.03989v2 Announce Type: replace Abstract: Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval preferences. We present Experience-RAG Skill, an agent-oriented pluggable retrieval orchestration layer positioned between the agent and the retriever pool. The proposed skill analyzes […]
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
arXiv:2605.06642v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit assignment over extended trajectories. In this work, we present Strategic Trajectory Abstraction (StraTA), a simple framework that introduces […]
TIDE: Every Layer Knows the Token Beneath the Context
arXiv:2605.06216v1 Announce Type: cross Abstract: We revisit a universally accepted but under-examined design choice in every modern LLM: a token index is looked up once at the input embedding layer and then permanently discarded. This single-injection assumption induces two structural failures: (i) the Rare Token Problem, where a Zipf-type distribution of vocabulary causes rare-token embeddings […]
Beyond Value Elicitation: Towards Moral Profiles in Early Requirements Engineering via Role-Playing Games and Anthropologist LLMs
arXiv:2510.01189v2 Announce Type: replace-cross Abstract: This study presents a proof of concept for eliciting and representing the moral profiles of digital system users in Requirements Engineering (RE) by combining immersive role-playing games (RPGs) with large language model (LLM) analysis. While existing approaches rely on predefined value taxonomies and explicit articulation, values are often tacit, context-dependent, […]
AROpt: An Optimization Method for Autoregressive Time Series Forecasting
arXiv:2602.02288v2 Announce Type: replace-cross Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) rollout. From the perspective of large language model training, traditional time-series forecasting model training ignores the monotonic error-growth heuristic. In this […]
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
arXiv:2605.06523v1 Announce Type: cross Abstract: Recent extensive research has demonstrated that the enhanced reasoning capabilities acquired by models through Reinforcement Learning with Verifiable Rewards (RLVR) are primarily concentrated within the rank-1 components. Predicated on this observation, we employed Periodic Rank-1 Substitution and identified a counterintuitive phenomenon: RLVR may exhibit implicit reward overfitting to the training […]
Overcoming Output Dimension Collapse: When Sparsity Enables Zero-shot Brain-to-Image Reconstruction at Small Data Scales
arXiv:2509.15832v3 Announce Type: replace Abstract: Advances in brain-to-image reconstruction are enabling us to externalize the subjective visual experiences encoded in the brain as images. A key challenge in this task is data scarcity: a translator that maps brain activity to latent image features is trained on a limited number of brain-image pairs, making the translator […]
Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems
arXiv:2604.11535v2 Announce Type: replace Abstract: Solving an NP-hard optimization problem often requires reformulating it for a specific solver — quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route any supported problem to any supported solver through a single interface. Building such a library […]
Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
arXiv:2505.21938v3 Announce Type: replace-cross Abstract: Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more practical threat model, Fake Data Injection, which reflects realistic adversarial constraints: the attacker can inject only a limited number of […]
Dynamic Expert-Guided Model Averaging for Causal Discovery
arXiv:2601.16715v2 Announce Type: replace-cross Abstract: Would-be practitioners of causal discovery face a dizzying array of algorithms without a clear best choice. This abundance of competitive methods makes ensembling a natural strategy for practical applications. At the same time, real-world use cases frequently violate the assumptions on which common causal discovery algorithms are based, forcing reliance […]
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
arXiv:2605.06157v1 Announce Type: cross Abstract: Image-Text-Matching (ITM) is one of the defacto methods of learning generalized representations from a large corpus in Vision and Language (VL). However, due to the weak association between the web-collected image-text pairs, models fail to show a fine-grained understanding of the combined semantics of these modalities. To address this issue […]