# 主题分类总览（阶段0输出）

> 基于 `AAAI2026_收藏论文.md` 全部 210 篇论文，按研究主题聚类。
> 论文引用格式：`Session · 论文N · 英文标题`（注意论文编号在每个 Session 内重新计数）。

## T01 自动驾驶感知与端到端驾驶

论文数：23

- Computer Vision III · 论文 38 · SPSC: Sparse and Scalable Multi-Modal 3D Occupancy Prediction for Autonomous Driving
- Computer Vision IV · 论文 27 · TSBOW – Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions
- Computer Vision IV · 论文 29 · STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes
- Computer Vision IV · 论文 37 · LidarPainter: One-Step Away from Any Lidar View to Novel Guidance
- Computer Vision V · 论文 13 · Exploring Surround-View Fisheye Camera 3D Object Detection
- Computer Vision VI · 论文 6 · Persistent Autoregressive Mapping with Traffic Rules for Autonomous Driving
- Computer Vision VI · 论文 13 · Improving Batch Normalization with Test-Time Adaptation for Robust Object Detection in Self-Driving
- Computer Vision VII · 论文 4 · CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving
- Computer Vision VII · 论文 51 · LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding
- Computer Vision VIII · 论文 56 · UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving
- Computer Vision XI · 论文 55 · HD²-SSC: High-Dimension High-Density Semantic Scene Completion for Autonomous Driving
- Computer Vision XI · 论文 64 · DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
- Computer Vision XII · 论文 15 · Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
- Computer Vision XII · 论文 23 · BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection
- Computer Vision XIII · 论文 71 · OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
- Computer Vision XIII · 论文 88 · Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space
- Machine Learning VIII · 论文 74 · Fine-flow Distilling Coarse-flow Video Generation for Long-Term Driving World Model
- Philosophy and Ethics of AI · 论文 24 · Any2Critical: Safety-Critical Scenario Generation from Arbitrary Real-World Driving Contexts
- Special Track on AI for Social Impact I · 论文 82 · Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
- Special Track on AI for Social Impact I · 论文 88 · KnowLCP: Knowledge Augmented Lane Change Prediction for Autonomous Driving
- AAAI Emerging Trends in AI · 论文 90 · Multimodal Coarse-to-Local Transformer for End-to-End Autonomous Driving (Student Abstract)
- AAAI Emerging Trends in AI · 论文 139 · Guided Latent Spaces for Controllable Multi-Scenario Generation in Autonomous Driving (Student Abstract)
- Application Domains I · 论文 21 · Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving

## T02 视频理解与视频多模态大模型

论文数：9

- Computer Vision III · 论文 3 · APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval
- Computer Vision III · 论文 7 · VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems
- Computer Vision IV · 论文 32 · GranAlign: Granularity-Aware Alignment Framework for Zero-shot Video Moment Retrieval
- Computer Vision V · 论文 38 · CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
- Computer Vision V · 论文 53 · TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
- Computer Vision V · 论文 77 · EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering
- Computer Vision VII · 论文 31 · Appearance-Motion Decomposed Alignment for Text-Video Retrieval
- Computer Vision XI · 论文 22 · UVLM: Benchmarking Video Language Model for Underwater World Understanding
- Computer Vision XII · 论文 71 · Introducing Decomposed Causality with Spatiotemporal Object-Centric Representation for Video Classification

## T03 图像多模态大模型与基础视觉

论文数：23

- Computer Vision V · 论文 9 · Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing
- Computer Vision V · 论文 35 · FIND: A Simple Yet Effective Baseline for Diffusion-Generated Image Detection
- Computer Vision V · 论文 62 · When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking
- Computer Vision VI · 论文 2 · OTI: A Model-free and Visually Interpretable Measure of Image Attackability
- Computer Vision VII · 论文 8 · UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing
- Computer Vision VII · 论文 62 · Infinite-Story: A Training-Free Consistent Text-to-Image Generation
- Computer Vision VII · 论文 66 · Generalized-Scale Object Counting with Gradual Query Aggregation
- Computer Vision VIII · 论文 12 · ImageSet2Text: Describing Sets of Images Through Text
- Computer Vision VIII · 论文 15 · MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models
- Computer Vision VIII · 论文 93 · Manipulation Intention Understanding for Zero-Shot Composed Image Retrieval
- Computer Vision XI · 论文 73 · Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing
- Computer Vision XII · 论文 68 · Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description
- Computer Vision XIII · 论文 108 · Decoupling What to Count and Where to See for Referring Expression Counting
- Machine Learning VI · 论文 84 · What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
- Machine Learning VIII · 论文 36 · X-SAM: From Segment Anything to Any Segmentation
- Machine Learning IX · 论文 18 · Positional Bias in Multimodal Embedding Models: Do They Favor the Beginning, the Middle, or the End?
- Machine Learning IX · 论文 20 · MPA: Multimodal Prototype Augmentation for Few-Shot Learning
- Machine Learning IX · 论文 66 · Adaptive Hallucination Alleviation in Multimodal Large Language Models: From Strategic Data Selection to Severity-Guided Training
- Natural Language Processing II · 论文 77 · Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input
- Natural Language Processing VI · 论文 25 · LLaVA-MS-PIT: Multi-Modal Schema-Guided Progressive Instruction Tuning for Multi-Modal Event Extraction
- AAAI Emerging Trends in AI · 论文 147 · Cumulant Attention in Vision Transformers (Student Abstract)
- AAAI Emerging Trends in AI · 论文 266 · Automated Multi-Camera Inspection System for Aircraft
- Machine Learning VII · 论文 97 · Trusted Multi-view Learning for Long-tailed Classification

## T04 3D视觉与空间智能

论文数：5

- Computer Vision III · 论文 14 · High-Quality Full-Head 3D Avatar Generation from Any Single Portrait Image
- Computer Vision XII · 论文 67 · Learning Better UAV-Based Cross-View Object Geo-Localization from Multi-Modal Prompts: MoP-UAV Benchmark and MoPT Framework
- Computer Vision XIII · 论文 49 · Paper Folding Puzzles: Can Multimodal Large Language Models Perform Spatial Reasoning?
- Computer Vision XIII · 论文 102 · HouseTune: Two-Stage Floorplan Generation with LLM Assistance
- Machine Learning III · 论文 1 · 4D Point Cloud Segmentation via Active Test-Time Adaptation

## T05 大模型高效训练与推理

论文数：28

- Computer Vision IV · 论文 48 · Less Is More: Rethinking Parameter-Efficient Fine-Tuning from a Subtractive Perspective
- Machine Learning I · 论文 68 · Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
- Machine Learning III · 论文 9 · DAVID: Dual-stage Adaptive Vision-text Integrated Decoupling for Multimodal KV Cache Eviction
- Machine Learning IV · 论文 86 · Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
- Machine Learning V · 论文 63 · Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts
- Machine Learning V · 论文 68 · Distilling Cross-Modal Knowledge via Feature Disentanglement
- Machine Learning VI · 论文 82 · ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization
- Machine Learning VI · 论文 83 · How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
- Machine Learning IX · 论文 52 · Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation
- Machine Learning IX · 论文 68 · CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
- Natural Language Processing I · 论文 22 · TIV: Thought Injection via Vectors for Efficient Reasoning in Large Reasoning Models
- Natural Language Processing II · 论文 40 · Hybrid Routing for a Mixture of LoRA Experts
- Natural Language Processing II · 论文 83 · From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning
- Natural Language Processing III · 论文 26 · GrayKD: Distilling Better Knowledge from Black-box LLM via Multi-rationale Injection
- Natural Language Processing III · 论文 94 · GateRA: Token-aware Modulation for Parameter-Efficient Fine-tuning
- Natural Language Processing IV · 论文 66 · PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
- Natural Language Processing IV · 论文 67 · KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
- Natural Language Processing IV · 论文 107 · LoKI: Low-Damage Knowledge Implanting of Large Language Models
- Natural Language Processing V · 论文 50 · LLM-Oriented Token-Adaptive Knowledge Distillation
- Natural Language Processing V · 论文 51 · Advanced Black-Box Tuning of Large Language Models with Limited API Calls
- Natural Language Processing V · 论文 67 · Test-time Prompt Intervention
- Natural Language Processing V · 论文 81 · RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
- Natural Language Processing VI · 论文 8 · MARS: Multimodal Adaptive Reasoning Model for Avoiding Overthinking
- Natural Language Processing VI · 论文 54 · SABER: Switchable and Balanced Training for Efficient LLM Reasoning
- Natural Language Processing VI · 论文 81 · In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback
- AAAI Emerging Trends in AI · 论文 220 · Algorithms for Context Engineering in LLM Inference: Optimization of Placement, Compression, and Scheduling
- AAAI Emerging Trends in AI · 论文 279 · AutoTuneX: Interactive Automated Fine-Tuning for Large Language Models
- Machine Learning VII · 论文 3 · Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling

## T06 LLM智能体与多智能体协作

论文数：20

- Computer Vision V · 论文 101 · Multi-Agent Undercover Gaming: Hallucination Removal Through Counterfactual Test for Multimodal Reasoning
- Application Domains II · 论文 62 · SoMe: A Realistic Benchmark for LLM-based Social Media Agents
- Computer Vision XII · 论文 85 · Evolving Generalist Virtual Agents with Generative and Associative Memory
- Data Mining and Knowledge Management III · 论文 53 · MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
- Machine Learning IV · 论文 16 · Multi-agent In-context Coordination via Decentralized Memory Retrieval
- Machine Learning VIII · 论文 26 · DAWN: Distributed LLM Multi-Agent Workflow Synthesis
- Multiagent Systems · 论文 3 · Efficient Multiagent Planning via Shared Action Suggestions
- Multiagent Systems · 论文 7 · GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents
- Multiagent Systems · 论文 46 · MACoT: Synthesizing Chains of Thought for Small Models via Multi-Agent Collaboration
- Multiagent Systems · 论文 48 · DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis
- Natural Language Processing II · 论文 3 · Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction
- Natural Language Processing II · 论文 46 · AutoTool: Efficient Tool Selection for Large Language Model Agents
- Natural Language Processing II · 论文 61 · WikiMAG: A Multi-Agent Guided Framework for Generating Structured Wikipedia-like Articles
- Natural Language Processing II · 论文 84 · From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions
- Natural Language Processing III · 论文 56 · InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
- Natural Language Processing VI · 论文 10 · ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries
- Natural Language Processing VI · 论文 13 · SlideTailor: Personalized Presentation Slide Generation for Scientific Papers
- AAAI Emerging Trends in AI · 论文 114 · Self-Guided Planning and Repair Framework for Code Generation (Student Abstract)
- AAAI Emerging Trends in AI · 论文 276 · ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation
- Cognitive Modeling and Cognitive Systems · 论文 35 · Agentic Design Review System

## T07A LLM安全（一）攻击越狱后门隐私

论文数：18

- Computer Vision X · 论文 1 · MTAttack: Multi-Target Backdoor Attacks Against Large Vision-Language Models
- Machine Learning III · 论文 14 · Poisoning with a Pill: Circumventing Detection in Federated Learning
- Machine Learning III · 论文 25 · On Robustness of Linear Classifiers to Targeted Data Poisoning
- Natural Language Processing I · 论文 53 · Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs
- Natural Language Processing I · 论文 54 · When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity
- Natural Language Processing II · 论文 10 · Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System
- Natural Language Processing III · 论文 12 · Query-Efficient Domain Knowledge Stealing Against Large Language Models
- Natural Language Processing V · 论文 75 · MrM: Black-Box Membership Inference Attacks Against Multimodal RAG Systems
- Philosophy and Ethics of AI · 论文 18 · 6DAttack: Backdoor Attacks in the 6DoF Pose Estimation
- Philosophy and Ethics of AI · 论文 21 · Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models
- Philosophy and Ethics of AI · 论文 26 · Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
- Philosophy and Ethics of AI · 论文 58 · MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers
- Philosophy and Ethics of AI · 论文 75 · Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
- Philosophy and Ethics of AI · 论文 79 · MacPrompt: Maraconic-Guided Jailbreak Against Text-to-Image Models
- Philosophy and Ethics of AI · 论文 82 · Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning
- Special Track on AI Alignment · 论文 49 · Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models
- Special Track on AI Alignment · 论文 84 · Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems
- Special Track on AI Alignment · 论文 98 · Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment

## T07B LLM安全（二）防御对齐与可信评估

论文数：26

- Application Domains II · 论文 90 · DIFT: Protecting Contrastive Learning Against Data Poisoning Backdoor Attacks
- Machine Learning X · 论文 75 · Vulnerability-Aware Robust Multimodal Adversarial Training
- Natural Language Processing I · 论文 20 · Does Question Really Matter? The Attribution of Answer Bias in LLM Evaluation
- Natural Language Processing II · 论文 90 · Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
- Natural Language Processing III · 论文 3 · Anti-adversarial Learning: Desensitizing Prompts for Large Language Model
- Natural Language Processing III · 论文 52 · Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
- Natural Language Processing IV · 论文 2 · WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking
- Natural Language Processing IV · 论文 36 · Fine-Tuned LLMs Know They Don’t Know: A Parameter-Efficient Approach to Recovering Honesty
- Natural Language Processing IV · 论文 63 · SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak Attacks
- Natural Language Processing IV · 论文 88 · SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models
- Natural Language Processing IV · 论文 101 · When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
- Philosophy and Ethics of AI · 论文 60 · ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
- Special Track on AI Alignment · 论文 24 · AlignTree: Efficient Defense Against LLM Jailbreak Attacks
- Special Track on AI Alignment · 论文 36 · Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
- Special Track on AI Alignment · 论文 48 · How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework
- Special Track on AI Alignment · 论文 55 · Mitigating Self-Preference by Authorship Obfuscation
- Special Track on AI Alignment · 论文 69 · Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal
- Special Track on AI Alignment · 论文 86 · STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
- Special Track on AI Alignment · 论文 90 · HumorReject: Decoupling LLM Safety from Refusal Prefix via a Little Humor
- Special Track on AI Alignment · 论文 105 · Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
- Special Track on AI for Social Impact II · 论文 53 · LLM Safety in Judicial AI: A Stress Test of Social Media Influence on Real-World Judgments
- AAAI Emerging Trends in AI · 论文 127 · Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract)
- AAAI Emerging Trends in AI · 论文 205 · Unveiling AI Safety in Fine-tuning Quantized Model
- AAAI Emerging Trends in AI · 论文 206 · When AI Meets AI: A Game-Theoretic Defense Framework Against AI Empowered Cyber Threats
- AAAI Emerging Trends in AI · 论文 261 · KnowThyself: An Agentic Assistant for LLM Interpretability
- Machine Learning VII · 论文 18 · LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

## T08 检索增强RAG与知识管理

论文数：11

- Computer Vision V · 论文 85 · RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding
- Data Mining and Knowledge Management III · 论文 9 · T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs
- Machine Learning III · 论文 33 · Forgetting by Pruning: Data Deletion in Join Cardinality Estimation
- Natural Language Processing I · 论文 15 · OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling
- Natural Language Processing I · 论文 41 · Improving Long-Context Summarization with Multi-Granularity Retrieval Optimization
- Natural Language Processing III · 论文 67 · RetroLM: Retrieval-Augmented KVs for Long-Context Processing
- Natural Language Processing III · 论文 68 · Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement
- Natural Language Processing IV · 论文 22 · Incorporating Token Importance in Multi-Vector Retrieval
- Natural Language Processing IV · 论文 30 · Are We on the Right Way to Assess Document Retrieval-Augmented Generation?
- Natural Language Processing IV · 论文 105 · ALEX:A Light Editing-knowledge Extractor
- Natural Language Processing VI · 论文 77 · Do Retrieval Augmented Language Models Know When They Don’t Know?

## T09 医疗AI与AI for Science

论文数：11

- Computer Vision V · 论文 5 · Versatile Vision-Language Model for 3D Computed Tomography
- Computer Vision V · 论文 37 · MIRA: Evaluating Multimodal AI on Complex Clinical Reasoning in Interventional Radiology
- Computer Vision VI · 论文 7 · Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs
- Computer Vision VI · 论文 44 · PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report Generation
- Computer Vision VI · 论文 89 · 3DTeethSAM: Taming SAM2 for 3D Teeth Segmentation
- Machine Learning I · 论文 21 · Medical Vision–Language Pretraining with LLM-Guided Temporal Supervision
- Multiagent Systems · 论文 57 · LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules
- Special Track on AI for Social Impact II · 论文 81 · Knowledge-Guided Machine Learning: A Paradigm Shift in AI for Science
- AAAI Emerging Trends in AI · 论文 106 · Can Large Language Models Grasp 3D Medical Anatomy Shapes? (Student Abstract)
- AAAI Emerging Trends in AI · 论文 186 · Fine-tuning Zero-shot Large Language Models for Patient-reported Outcomes (Student Abstract)
- Application Domains I · 论文 63 · RAG-Enhanced Collaborative LLM Agents for Drug Discovery

## T10 认知心理教育与人机交互

论文数：22

- Application Domains II · 论文 38 · PsyPARSE: Retrieval-Augmented Slow Thinking for Personalized Empathetic Counseling
- Data Mining and Knowledge Management III · 论文 34 · Making Visual Dialogue More Engaging: A New Task, Method, and Metric
- Humans and AI · 论文 40 · Simulating Human-Like Counseling: A Path- and Scenario-Guided Framework for Psychological Support Dialogue
- Humans and AI · 论文 47 · Consensus-Driven Multi-Agent Cognitive Reasoning for Enhancing the Emotional Intelligence of Large Language Models
- Multiagent Systems · 论文 53 · An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling
- Natural Language Processing I · 论文 60 · Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM
- Natural Language Processing I · 论文 62 · Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs
- Natural Language Processing II · 论文 71 · The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models
- Natural Language Processing III · 论文 35 · Easy for Children, Hard for AI: The Limits of Multimodal LLMs in Early Childhood Learning
- Natural Language Processing IV · 论文 14 · Are Language Models Any Good at Density Modeling?
- Natural Language Processing V · 论文 85 · Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning
- Philosophy and Ethics of AI · 论文 34 · The Other Mind: How Language Models Exhibit Human Temporal Cognition
- Philosophy and Ethics of AI · 论文 48 · An Epistemic Perspective on Agent Awareness
- Special Track on AI Alignment · 论文 61 · Quiet Feature Learning in Algorithmic Tasks
- Special Track on AI for Social Impact II · 论文 16 · CCD-Bench: Probing Cultural Conflict in Large Language Model Decision-Making
- AAAI Emerging Trends in AI · 论文 16 · Model AI Assignments 2026
- AAAI Emerging Trends in AI · 论文 264 · Steve: Your Personal AI Career Coach
- Cognitive Modeling and Cognitive Systems · 论文 1 · Hypothesis-Driven Reasoning for Large Language Models
- Cognitive Modeling and Cognitive Systems · 论文 25 · ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction
- Cognitive Modeling and Cognitive Systems · 论文 32 · Mind the Gap: The Divergence Between Human and LLM-Generated Tasks
- Cognitive Modeling and Cognitive Systems · 论文 39 · Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier
- Cognitive Modeling and Cognitive Systems · 论文 66 · Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback

## T11 金融AI与决策

论文数：5

- Application Domains II · 论文 24 · TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domains
- AAAI Emerging Trends in AI · 论文 183 · Do Large Language Models (LLMs) Understand Chronology? (Student Abstract)
- AAAI Emerging Trends in AI · 论文 284 · PortfolioPilot: An Agentic Platform for Financial Portfolio Management Algorithm Development and Evaluation
- Machine Learning VII · 论文 47 · Kronos: A Foundation Model for the Language of Financial Markets
- Application Domains I · 论文 57 · FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation

## T12 强化学习与机器人

论文数：9

- Computer Vision IV · 论文 31 · JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics
- Humans and AI · 论文 43 · Reducing Goal State Divergence with Environment Design
- Intelligent Robotics · 论文 26 · Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology
- Intelligent Robotics · 论文 30 · DiTEA: Mixture-of-Experts for Vision-Language-Action Model in Robotic Manipulation
- Machine Learning V · 论文 82 · IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environments
- Special Track on AI for Social Impact II · 论文 77 · Multi-Armed Bandits Meet Large Language Models
- AAAI Emerging Trends in AI · 论文 22 · Multi-Objective Search: Algorithms, Applications, and Emerging Directions
- AAAI Emerging Trends in AI · 论文 254 · PANSim: Visualization Tool for Planning and Acting against Nature
- Machine Learning VII · 论文 79 · Complex Instruction Following with Diverse Style Policies in Football Games