127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “llm”

22,024 results

Agents

SecureVibe: Making Vibe Coding More Secure

DGX agent

arXiv:2609.38606v1 Announce Type: cross Abstract: As vibe coding becomes increasingly capable and widespread, security vulnerabilities in even functionally correct solutions are a growing concern. Whe

agentsarxiv-cs-cl

1 Oct 2026

Model Releases

Structure of Basic Human Values in Russian Social Media

DGX agent

arXiv:2603.18822v2 Announce Type: replace Abstract: What is known about the values of national populations rests almost entirely on questionnaires, which prompt respondents to rate researcher-supplied

Search: “llm”

SecureVibe: Making Vibe Coding More Secure

Structure of Basic Human Values in Russian Social Media

Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail

Turbo Harness: Instance-Adaptive Harness Optimization

When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate

Zero2Repo: Can Coding Agents Build Repositories from Scratch?

A foundation model for energy and radiation systems built on heterogeneous scientific interfaces

A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses

ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation

Beyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models

Binarization Flattens the Score Space

Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery

ContextRender: From Execution Dependencies to Agent Context

CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering

Effective Dense Retrieval using Only In-Context Examples

From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework

JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

LatCom: Cross-Agent Latent Compression for Efficient Multi-Agent Collaboration

Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning

Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents

RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems

Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection

SAGE: A Statistical Acceptance Gate for Self-Evolving Agents

Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection

SEED: Self-Speculative Decoding via Implicit Encoder-Decoder

SelfSearch: Reward-Free Search for Self-Improving Agents

'Shall We Play a Game?' - H3 - Wargames(83) ending [Spoiler] recreated using 4 stills and a sample of Joshua's voice. (Claude Fable on 3rd try vs. Astra)

SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation

TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning

UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG

UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?

UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval

Vulnerability Discovery and Exploitation Trends in the AI Era

Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition

BiasReducer: Adaptive Bias Mitigation for Reward Models

Certified Multi-Source Integrity for Structured Agent Actions

Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery

Contrast Matters: Understanding Robustness of In-Context Fine-Tuning to Target-Context Relatedness

Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret

Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference

Do World Models Learn Global Understanding?

EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents?

From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis

GenMem: Generative Symbolic Memory for Self-Evolving Harness

Large Language Models for Automated Cross-Domain Machine Learning Task Type Identification: A Benchmark Dataset and Evaluation

QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents

Reflection 70B was released two years ago (September 2024)