SpaceAct
Across 10 frontier MLLMs on the 44 hardest instances, scores span 4.8-79.1, with seven solving at most 27.3% of 6-DoF tasks.
Benchmarking 3D Spatial and Temporal Reasoning via Closed-Loop Action and Active Perception
AI Research Radar
Friday, October 30: 6 frontier papers out of 734 read.
Frontier
Papers rated as moving the field
How we chooseAgentic Backdoors via Pretraining Poisoning
Poisoning 0.1% of the pretraining corpus implants a remote code execution backdoor in Qwen3 CLI agents, reaching roughly 92% ASR at 4B scale.
Nemotron 3.5 Super and Lightning
Nemotron 3.5 Super achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra with approximately 4.6x fewer active parameters.
Scaling Lean Theorem Proving for Real-World Code Verification
EasyProver proves 52.7% of 2,000 sampled Aegis statements within a 30-minute budget per statement.
SPARSEBLEED
SparseBleed bypasses state-of-the-art privacy defenses, inferring Sex with 66.39% accuracy and Surgical Procedure with 99.8% accuracy on Texas-100X from a single query.
Skillful and realistic precipitation forecasting with reinforced diffusion
The reinforced diffusion model FitzRoy matches or exceeds state-of-the-art precipitation forecasts over the continental United States while preserving structural realism and capturing extreme events.
This week in research
Oct 24–30: 232 cleared, 15 frontier
- Security83◆ 3
- Safety39◆ 3
- Agents36◆ 1
- Society20
- Robotics17◆ 2
- 4 moreTraining, Science, ML, Reasoning15◆ 5
- Vision8◆ 1
- Inference8
- Language6
- Security83◆ 3
- 8 moreRobotics, Vision, Inference, Language, Training, Science, ML, Reasoning54◆ 8
- Safety39◆ 3
- Agents36◆ 1
- Society20
Size: cleared papers◆ and tint: frontier papers
Models under test
Papers this week that name the model
Labs publishing
Papers this week with an author at the lab
Also cleared
71 papers, by field
Security & privacy26
- Post-Training Large Language Models with LLMONIBM
- Where You Inject Matters: The Trust Region Effect in LLM AgentsMicrosoft
- TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless RacesMeta
- Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt InjectionCode
- Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language ModelsCode
All 26 papers in Security & privacy
- Poisoned Skills: Propagating Jailbreaks Through Agent Markdown Files
- Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs
- Jailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak
- Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger
- Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction
- WebMaze: Defending Against LLM-Powered Web Scanners with Functionality-Coupled Deception
- A Minimally Informed Black-Box Fake-Report Attack on DRL Traffic-Signal Control
- Session-Bound Behavioral Watermarking for Autonomous LLM Agents
- Discovering Jailbreaks via Curriculum of Models
- FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models
- PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
- REALM: Identifying Minimal Task Assets for LLM Agents
- CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
- Provably Secure Diffusion Watermarking Against Removal Adversaries with Batched Detector Access
- Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
- SEAL: Sealed Queries for Local Sanitization against Indirect Prompt Injection
- InferD: A Honeypot Framework for AI Inference Infrastructure
- PASA-KV: Attacking Action-Facing Visual Routes in World Action Models
- Understanding and Mitigating Role Spoofing in LLMs
- Preserving Utility in Continual LLM Unlearning via Orthogonal Projections
- The Privacy and Security Risks of Edge LLM Optimization
Safety & alignment13
- What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed UncertaintyMeta
- ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn DefenderMicrosoft
- Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data
- Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening
- Who Else Is In? Multi-Agent Collusion Initation Via Strategic Vagueness
All 13 papers in Safety & alignment
- Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
- When Support Crosses the Line: Evaluating Ethical Boundaries in LLM-Based Mental Health Support in the Chinese Context
- An Alignment Benchmark for Enterprise Agents on Era by Eon
- Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness
- AgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure
- Sticky Collusion: Persistence of LLM Agent Collusion after Incentive Removal and Partner Replacement
- How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
- Pre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
AI & society9
- FYC: FPR-Disparity Weight Perturbation and Youden Calibration for Fair Deepfake Detection
- AI-Generated Non-Consensual Intimate Imagery is Configured, Not Built: How General-Purpose AI Technology Enables Sexual Violence
- Algorithmic Bias from the Perspectives of Healthcare Professionals
- Disparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems
- The Indian Financial Automated Advice Bias (IFAAB) Dataset : Auditing Socioeconomic and Demographic Disparities in LLM-Generated Financial Advice in India
All 9 papers in AI & society
Agents7
- Think Before You Act: Decision Gate for LLM AgentsIBM
- Blind Spots: Where Small Language Models Fall Behind Frontier Models on Terminal TasksMicrosoft
- KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising AgentsAlibaba
- A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI AcceleratorCode
- When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills
Vision & multimodal4
- Where Do Vision Language Models Fail at 3D Reasoning?Code
- Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage
- IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation
- Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe