Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
arXiv:2604.05549v1 Announce Type: new Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact...
Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
arXiv:2604.05497v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language models (dMLLMs). These...
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
arXiv:2604.05018v1 Announce Type: new Abstract: Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a...
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
arXiv:2604.05242v1 Announce Type: new Abstract: Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still...
A mathematical theory of evolution for self-designing AIs
arXiv:2604.05142v1 Announce Type: new Abstract: As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may emerge, in which the traits of AI systems are shaped by the success of earlier AIs in designing and...
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs
arXiv:2604.05643v1 Announce Type: new Abstract: Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating...
CODESTRUCT: Code Agents over Structured Action Spaces
arXiv:2604.05407v1 Announce Type: new Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where...
LMI-Net: Linear Matrix Inequality--Constrained Neural Networks via Differentiable Projection Layers
arXiv:2604.05374v1 Announce Type: new Abstract: Linear matrix inequalities (LMIs) have played a central role in certifying stability, robustness, and forward invariance of dynamical systems. Despite rapid development in learning-based methods for control design and certificate synthesis, existing approaches often fail...
Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings
arXiv:2604.05613v1 Announce Type: new Abstract: Autoregressive graph generators define likelihoods via a sequential construction process, but these likelihoods are only meaningful if they are consistent across all linearizations of the same graph. Segmented Eulerian Neighborhood Trails (SENT), a recent linearization...
I can’t help rooting for tiny open source AI model maker Arcee
Arcee is a tiny 26-person U.S. startup that built a high-performing, massive, open source LLM. And it's gaining popularity with OpenClaw users.
Testing the Limits of Truth Directions in LLMs
arXiv:2604.03754v1 Announce Type: new Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous studies have argued that these directions are universal in certain aspects, while more...
Position: Science of AI Evaluation Requires Item-level Benchmark Data
arXiv:2604.03244v1 Announce Type: new Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain...
Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
arXiv:2604.03809v1 Announce Type: new Abstract: Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and measure pairwise similarity: across...
Affording Process Auditability with QualAnalyzer: An Atomistic LLM Analysis Tool for Qualitative Research
arXiv:2604.03820v1 Announce Type: new Abstract: Large language models are increasingly used for qualitative data analysis, but many workflows obscure how analytic conclusions are produced. We present QualAnalyzer, an open-source Chrome extension for Google Workspace that supports atomistic LLM analysis by...
Announcing the ICML 2026 Workshops and Affinity Workshops
I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
arXiv:2604.03904v1 Announce Type: new Abstract: Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interventions -- explicitly announcing reward schemes for answer-versus-abstain decisions...
Startup Battlefield 200 applications open: a chance for VC access, TechCrunch coverage, and $100K
Nominate your startup, or one you know that deserves the spotlight, and finish the process by applying. Selected 200 have a chance at VC access, TechCrunch coverage, and $100K for Startup Battlefield 200. Applications close on May 27.
Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports
arXiv:2604.03664v1 Announce Type: new Abstract: Despite the strong language understanding abilities of large language models (LLMs), they still struggle with reliable question answering (QA) over long, structured documents, particularly for numerical reasoning. Financial annual reports exemplify this difficulty: financial statement...
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
arXiv:2604.03877v1 Announce Type: new Abstract: Analogical reasoning is a core cognitive faculty essential for narrative understanding. While LLMs perform well when surface and structural cues align, they struggle in cases where an analogy is not apparent on the surface but...
Automated Conjecture Resolution with Formal Verification
arXiv:2604.03789v1 Announce Type: new Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving to increasingly capable performance on research-level problems. However, reliably solving and verifying such problems remains...
Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty
arXiv:2604.04182v1 Announce Type: new Abstract: Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as sequential decision policies in a two-option probabilistic reversal-learning task with three latent states and switch...
Are Arabic Benchmarks Reliable? QIMMA's Quality-First Approach to LLM Evaluation
arXiv:2604.03395v1 Announce Type: new Abstract: We present QIMMA, a quality-assured Arabic LLM leaderboard that places systematic benchmark validation at its core. Rather than aggregating existing resources as-is, QIMMA applies a multi-model assessment pipeline combining automated LLM judgment with human review...
Delayed Homomorphic Reinforcement Learning for Environments with Delayed Feedback
arXiv:2604.03641v1 Announce Type: new Abstract: Reinforcement learning in real-world systems is often accompanied by delayed feedback, which breaks the Markov assumption and impedes both learning and control. Canonical state augmentation approaches cause the state-space explosion, which introduces a severe sample-complexity...
Neural Global Optimization via Iterative Refinement from Noisy Samples
arXiv:2604.03614v1 Announce Type: new Abstract: Global optimization of black-box functions from noisy samples is a fundamental challenge in machine learning and scientific computing. Traditional methods such as Bayesian Optimization often converge to local minima on multi-modal functions, while gradient-free methods...
Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
arXiv:2604.03962v1 Announce Type: new Abstract: In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over partial...
Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach
arXiv:2604.03533v1 Announce Type: new Abstract: We present an automated crosswalk framework that compares an AI safety policy document pair under a shared taxonomy of activities. Using the activity categories defined in Activity Map on AI Safety as fixed aspects, the...
Choosing the Right Regularizer for Applied ML: Simulation Benchmarks of Popular Scikit-learn Regularization Frameworks
arXiv:2604.03541v1 Announce Type: new Abstract: This study surveys the historical development of regularization, tracing its evolution from stepwise regression in the 1960s to recent advancements in formal error control, structured penalties for non-independent features, Bayesian methods, and l0-based regularization (among...
Self-Execution Simulation Improves Coding Models
arXiv:2604.03253v1 Announce Type: new Abstract: A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code LLMs can...
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information...