Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
arXiv:2604.03174v1 Announce Type: new Abstract: Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account of augmentation...
SIEVE: Sample-Efficient Parametric Learning from Natural Language
arXiv:2604.02339v1 Announce Type: new Abstract: Natural language context-such as instructions, knowledge, or feedback-contains rich signal for adapting language models. While in-context learning provides adaptation via the prompt, parametric learning persists into model weights and can improve performance further, though is...
Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection
arXiv:2604.02819v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all teacher-generated reasoning trajectories...
Revealing the Learning Dynamics of Long-Context Continual Pre-training
arXiv:2604.02650v1 Announce Type: new Abstract: Existing studies on Long-Context Continual Pre-training (LCCP) mainly focus on small-scale models and limited data regimes (tens of billions of tokens). We argue that directly migrating these small-scale settings to industrial-grade models risks insufficient adaptation...
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
arXiv:2604.02709v1 Announce Type: new Abstract: The formal reasoning capabilities of LLMs are crucial for advancing automated software engineering. However, existing benchmarks for LLMs lack systematic evaluation based on computation and complexity, leaving a critical gap in understanding their formal reasoning...
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
arXiv:2604.02340v1 Announce Type: new Abstract: Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full-sequence denoising passes with a large Transformer and, unlike autoregressive decoding,...
Compositional Neuro-Symbolic Reasoning
arXiv:2604.02434v1 Announce Type: new Abstract: We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly symbolic systems struggle with perceptual grounding. We...
LLM Reasoning with Process Rewards for Outcome-Guided Steps
arXiv:2604.02341v1 Announce Type: cross Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such pipelines optimize outcome correctness only,...
R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning
arXiv:2604.03004v1 Announce Type: new Abstract: While deep reasoning with long chain-of-thought has dramatically improved large language models in verifiable domains like mathematics, its effectiveness for open-ended tasks such as writing remains unexplored. In this paper, we conduct a systematic investigation...
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
arXiv:2604.02460v1 Announce Type: new Abstract: Recent work reports strong performance from multi-agent LLM systems (MAS), but these gains are often confounded by increased test-time computation. When computation is normalized, single-agent systems (SAS) can match or outperform MAS, yet the theoretical...
Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
arXiv:2604.02653v1 Announce Type: new Abstract: Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical explanations of...
Beyond Message Passing: Toward Semantically Aligned Agent Communication
arXiv:2604.02369v1 Announce Type: cross Abstract: Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired perspective on this emerging...
Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding
arXiv:2604.03201v1 Announce Type: new Abstract: Agentic AI is increasingly judged not by fluent output alone but by whether it can act, remember, and verify under partial observability, delay, and strategic observation. Existing research often studies these demands separately: robotics emphasizes...
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
arXiv:2604.02947v1 Announce Type: new Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a...
Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network
arXiv:2604.02342v1 Announce Type: new Abstract: In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in tasks such as node classification, link prediction, and graph representation learning. However, they remain susceptible to biases that can arise not only from...
Dynamic Mask Enhanced Intelligent Multi-UAV Deployment for Urban Vehicular Networks
arXiv:2604.02358v1 Announce Type: cross Abstract: Vehicular Ad Hoc Networks (VANETs) play a crucial role in realizing vehicle-road collaboration and intelligent transportation. However, urban VANETs often face challenges such as frequent link disconnections and subnet fragmentation, which hinder reliable connectivity. To...
Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
arXiv:2604.02795v1 Announce Type: new Abstract: Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level rewards, introducing severe reward sparsity and...
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
arXiv:2604.02972v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or derivation errors; II) Inter-step...
Supreme Court issues statement that Justice Alito was hospitalized approximately two weeks ago
Justice Samuel Alito was hospitalized on March 20 “[o]ut of an abundance of caution” and at the recommendation of his security detail, the Supreme Court’s Public Information Officer, Patricia McCabe, […]The postSupreme Court issues statement that Justice Alito was hospitalized...
What oral argument told us in the birthright citizenship case
Empirical SCOTUS is a recurring series by Adam Feldman that looks at Supreme Court data, primarily in the form of opinions and oral arguments, to provide insights into the justices’ decision making and […]The postWhat oral argument told us in...
The inscrutable Chief Justice John Roberts
As much of the legal media (including SCOTUSblog) reported last month, Chief Justice John Roberts offered some rare public remarks in an appearance at Rice University, rebuking personal attacks on […]The postThe inscrutable Chief Justice John Robertsappeared first onSCOTUSblog.
SCOTUStoday for Friday, April 3
Comedian John Mulaney appeared on “The Late Show with Stephen Colbert” earlier this week and gave a shoutout to SCOTUSblog as he described being a “Supreme Court argument nerd.” Mama, […]The postSCOTUStoday for Friday, April 3appeared first onSCOTUSblog.
Trump ignores biggest reasons his AI data center buildout is failing
Nearly 50% of data center projects delayed as China holds key to power infrastructure.
Netflix must refund customers for years of price hikes, Italian court rules
Consumer group says it will sue if Netflix doesn't reduce current prices.
The Privileges or Immunities Clause, Abridged: A Critique of Kurt Lash on the Fourteenth Amendment
ARTICLE The Privileges or Immunities Clause, Abridged: A Critique of Kurt Lash on the Fourteenth Amendment Randy E. Barnett* & Evan D. Bernick** The Privileges or Immunities Clause of the Fourteenth Amendment reads: “No State shall make or enforce any...
The Enumerated-Rights Reading of the Privileges or Immunities Clause: A Response to Barnett and Bernick
ARTICLE The Enumerated-Rights Reading of the Privileges or Immunities Clause: A Response to Barnett and Bernick Kurt T. Lash* In 1871, John Bingham explained the meaning of the Fourteenth Amendment’s Privileges or Immunities Clause—a clause Bingham himself drafted and had...
Improving Latent Generalization Using Test-time Compute
arXiv:2604.01430v1 Announce Type: new Abstract: Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary strengths, in-weights learning frequently struggles to...
Soft MPCritic: Amortized Model Predictive Value Iteration
arXiv:2604.01477v1 Announce Type: new Abstract: Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet combining them at scale remains computationally challenging. We propose soft MPCritic, an RL-MPC framework that learns in (soft) value space while using sample-based...
PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
arXiv:2604.00931v2 Announce Type: new Abstract: Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice and accumulated experience. To bridge this...