AI reviews for all 22,977 AAAI-26 papers were preferred by authors and PC members over human reviews on accuracy and suggestions and outperformed baselines at spotting weaknesses.
super hub Mixed citations
OpenAI GPT-5 System Card
Mixed citation behavior. Most common role is background (51%).
358
Pith papers citing it
Background
51% of classified citations
abstract
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.
hub tools
citation-role summary
background 43
baseline 23
method 7
dataset 3
other 3
citation-polarity summary
claims ledger
- abstract This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits ar
co-cited works
representative citing papers
Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO post-training.
AMNESIA is a benchmark suite of 70,560 medical QA pairs that evaluates unlearning methods and shows that patient-level unlearning erodes disease-shared knowledge.
FlowCompile performs compile-time design space exploration on structured LLM workflows to produce reusable high-quality configuration sets that outperform routing baselines with up to 6.4x speedup.
M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
Soohak is a 439-problem mathematician-curated benchmark where frontier LLMs reach at most 30.4% on research math challenges and no model exceeds 50% on refusal for ill-posed problems.
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
EVE enables verifiable self-evolution of MLLMs by using a Challenger-Solver architecture to generate dynamic executable visual transformations that produce VQA problems with absolute execution-verified ground truth.
VLMs hallucinate by prioritizing contradictory on-screen text over visual content, addressed via the VisualTextTrap benchmark with 6,057 human-validated samples and the VTHM-MoE dual-encoder framework using dimension-specific experts and adaptive routing.
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
DragOn provides a new drag-grounding benchmark and training dataset for GUI agents, with evaluations suggesting potential improvements on computer-use tasks.
OmniOPD replaces token-level logit matching in on-policy distillation with Monte Carlo chunk-level semantic verification and a peak-entropy scheduler.
MM-Snowball benchmark diagnoses hallucination snowballing in multi-turn MLLM dialogues; CAVR mitigates it via dual visual rectification at representation and logit levels.
Moral Trolley Arena shows frontier LLMs produce composite moral preferences that are compressed rather than additive functions of calibrated component act strengths across Moral Foundations Theory.
Frontier VLMs overconfidently answer spatial questions under occlusion (~30% accuracy) and perspective ambiguity (<10% accuracy) instead of abstaining, and often fail to select helpful additional views.
VLMs exhibit consistent vertical-distance entanglement in embeddings from perspective bias in natural images, producing accuracy gaps that a new synthetic benchmark SpatialTunnel exposes as model-intrinsic.
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
CardioLens is a leakage-resistant CMR testbed of 473k slices and 13k QA pairs showing current MLLMs exhibit a large clinical reality gap with category-collapse failures on real workflows.
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
Introduces MUTATE benchmark for path-level and action-level divergent thinking in LLM agents and ReDNA method that decouples divergent generation from convergent selection to improve performance.
SD-MIA is a black-box membership inference attack that detects pre-training data in diffusion models via cross-modal perturbations on images and textual instructions.
Introduces EHR-ReasonCon benchmark with expert annotations and EHR-Inspector LLM framework for reasoning-intensive verification of consistency between clinical notes and structured tables in EHRs.
JobBench is a new benchmark with 130 occupational tasks where the best of 36 tested AI models achieves only 45.9% success.
citing papers explorer
-
Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
Local calibration of likelihood ratios conditioned on hidden-space position corrects Simpson's paradox in token averaging and substantially improves machine-text detection across baselines.
-
Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges
LLM safety judges flip verdicts on equivalent policy rewrites up to 9.1% of the time and cannot distinguish meaningful from meaningless changes, requiring new invariance-based reliability metrics.
-
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
Context-ReAct enables agents to dynamically manage context via five atomic operations, and LongSeeker fine-tuned on 10k trajectories achieves 61.5% and 62.5% on BrowseComp benchmarks, outperforming prior agents.
-
DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning
DiffCap-Bench supplies a diverse IDC benchmark with ten categories and LLM judging grounded in human difference lists to evaluate MLLMs more robustly than prior lexical metrics.
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing prefixes to semantic neighbors during training creates a hierarchical noise model that improves language model predictions on token sequences outside the training corpus support.
-
Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
Chart-FR1 uses Focus-CoT for linking reasoning to visual cues and Focus-GRPO reinforcement learning with efficiency rewards to outperform prior MLLMs on dense chart reasoning tasks.
-
AI Alignment Amplifies the Role of Race, Gender, and Disability in Hiring Decisions
Post-training alignment amplifies hiring advantages for female and Black candidates by over 300 percent and disadvantages for disabled candidates by 171 percent, reversing some human discrimination patterns.
-
GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models
GR-Ben is a new process-level benchmark that evaluates error detection by PRMs and LLMs in science and logic reasoning, showing weaker performance outside mathematics.
-
MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction
MUDY improves unsupervised keyphrase extraction by combining prompt-based scoring with candidate-aware weighting and self-attention-based multi-granular scoring to capture both local and global contextual salience, outperforming baselines on four datasets.
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
-
DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation
A scalable training-free pipeline using video segmentation, filtering, and off-the-shelf multimodal models creates DenseStep2M, a dataset of 100K videos and 2M detailed instructional steps that improves dense captioning, step grounding, and cross-modal retrieval.
-
Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding
MCM-VG achieves state-of-the-art zero-shot 3D visual grounding on ScanRefer and Nr3D by creating consistent 2D-3D mappings across semantic, geometric, and viewpoint dimensions using LLMs and VLMs.
-
MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation
MEMCoder boosts LLM code generation for private libraries by 16.31% pass@1 via a multi-dimensional evolving memory that distills usage guidelines from execution feedback and combines them with static docs.
-
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing
Spore extracts private data from LLM memory with one query in black-box mode or ranked tokens in gray-box, outperforming prior attacks while bypassing defenses.
-
AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs
AutoPyVerifier learns compact sets of executable Python verifiers from labeled LLM outputs via LLM synthesis and DAG search, improving objective prediction by up to 55 F1 points and downstream LLM accuracy by up to 17 points.
-
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Using contrastive examples with vision-language models and a new CLIP-based scoring method called CSP produces more faithful and granular neuron labels than prior activation-only approaches.
-
Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Design
Mol-Debate applies multi-agent debate in an iterative loop with perspective orchestration to achieve state-of-the-art text-guided molecular design, scoring 59.82% exact match on ChEBI-20 and 50.52% weighted success on S2-Bench.
-
Infection-Reasoner: A Compact Vision-Language Model for Wound Infection Classification with Evidence-Grounded Clinical Reasoning
Infection-Reasoner, a 4B VLM, reaches 86.8% accuracy on wound infection classification while producing rationales rated mostly correct by experts, via GPT-5.1 distillation followed by reinforcement learning.
-
Beyond Rating: A Comprehensive Evaluation and Benchmark for AI Reviews
Beyond Rating proposes five text-centric metrics for AI reviewers and demonstrates that aligning AI focus on paper weaknesses with human experts is required for reliable automated review scoring.
-
How Adversarial Environments Mislead Agentic AI?
Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.
-
LLM-AUG: Robust Wireless Data Augmentation with In-Context Learning in Large Language Models
LLM-AUG applies LLM in-context learning for embedding-space data augmentation in wireless ML, outperforming baselines and reaching near-oracle accuracy with only 15% labeled data on RadioML and IC datasets.
-
Characterizing Model-Native Skills
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
-
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
Omni-modal LLMs exhibit visual preference that emerges in mid-to-late layers, enabling hallucination detection without task-specific training.
-
Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
VLMs primarily reason in textual space with limited reliance on visual evidence, shown by consistent performance drops when images are added to text in a controlled aligned benchmark.
-
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Lightning OPD is an offline on-policy distillation method that matches standard OPD performance at 4x efficiency by enforcing teacher consistency between SFT and distillation phases.
-
Narrative-Driven Paper-to-Slide Generation via ArcDeck
ArcDeck models paper-to-slide generation as narrative reconstruction using discourse parsing and multi-agent refinement, plus a new ArcBench benchmark, to improve flow and coherence over direct summarization.
-
GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays
GazeVaLM provides 960 gaze recordings from 16 radiologists on 60 chest X-rays (half synthetic) plus LLM predictions for diagnostic accuracy and real-fake detection under matched conditions.
-
Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
R^3 optimizes full scientific applications on GPUs better than tuning kernel parameters or compiler flags alone while running nearly an order of magnitude faster than modern evolutionary search methods.
-
When LLMs Lag Behind: Knowledge Conflicts from Evolving APIs in Code Generation
LLMs produce executable code only 42.55% of the time under API evolution without full documentation, improving to 66.36% with structured docs and by 11% more with reasoning strategies, yet outdated patterns persist.
-
UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding
UniversalVTG is a lightweight foundation model for video temporal grounding that achieves state-of-the-art results across five benchmarks while being over 100 times smaller than recent MLLM-based methods.
-
SeLaR: Selective Latent Reasoning in Large Language Models
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
-
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
BAIM enriches knowledge tracing item representations by deriving stage-level embeddings from Polya's four problem-solving stages and routing them adaptively per learner context, yielding consistent gains over pretraining baselines on two datasets.
-
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
-
Linear Representations of Hierarchical Concepts in Language Models
Language models encode concept hierarchies as linear transformations that are domain-specific yet structurally similar across domains.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views
AV-SQL uses a pipeline of LLM agents to generate intermediate CTE views that decompose complex Text-to-SQL queries, reaching 70.38% execution accuracy on Spider 2.0.
-
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
-
Exclusive Unlearning
Exclusive Unlearning makes LLMs safe by forgetting all but retained domain knowledge, protecting against jailbreaks while preserving useful responses in areas like medicine and math.
-
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
GUIDE unrolls multi-granularity geometric priors layer-wise into early MLLM layers with gating to improve spatial reasoning and perception.
-
EchoAgent: Towards Reliable Echocardiography Interpretation with "Eyes","Hands" and "Minds"
EchoAgent is a new agentic AI system that integrates visual observation, quantitative measurement, and expert knowledge reasoning to achieve reliable echocardiography interpretation with up to 80% accuracy on CAMUS and MIMIC-EchoQA datasets.
-
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Video-MME-v2 is a new benchmark that applies progressive visual-to-reasoning levels and non-linear group scoring to expose gaps in video MLLM capabilities.
-
An Independent Safety Evaluation of Kimi K2.5
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
-
Mitigating LLM biases toward spurious social contexts using direct preference optimization
Debiasing-DPO reduces bias to spurious social contexts by 84% and improves predictive accuracy by 52% on average for LLMs evaluating U.S. classroom transcripts.
-
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
-
From Data to Theory: Autonomous Large Language Model Agents for Materials Science
An LLM agent autonomously selects, codes, and validates materials equations from data, recovering known laws reliably but requiring checks for new or specialized cases.
-
Evaluating Privilege Usage of Agents with Real-World Tools
GrantBox evaluates LLM agents using real-world tools and finds they remain vulnerable to sophisticated prompt injection attacks with an 84.80% average success rate.
-
AIRA_2: Overcoming Bottlenecks in AI Research Agents
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
-
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
An external zero-shot monitor detects nine unsafe reasoning behaviors in LLMs at 87% step-level accuracy with low false positives and low latency.
-
Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
Safety degradation in large reasoning models occurs only after chain-of-thought is enabled; adding pre-CoT safety signals from a BERT classifier on safe models improves safety while preserving reasoning ability.
-
Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks
PulseFocus improves multi-image reasoning in VLMs by interleaving planning and attention-gated focus blocks during chain-of-thought, achieving gains on BLINK and MuirBench.