16
DeepTutor: Towards Agentic Personalized Tutoring
DeepTutor is an open-source agentic framework that combines citation-grounded tutoring with calibrated feedback to personalize educational interactions.
16
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
Researchers proposed an SVD-based vision token pruning method to reduce the computational and memory overhead of processing long sequences in Vision-Language Models.
16
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
The paper introduces a harness-engineering architecture designed to make enterprise large language model agents more traceable, deterministic, and auditable.
16
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
The paper introduces ContextSniper, a token-efficient code memory module designed to select precise evidence for repository-level program repair using language model agents.
16
SLORR: Simple and Efficient In-Training Low-Rank Regularization
Researchers developed SLORR, an in-training low-rank regularization method designed to make neural networks more compressible without requiring complex matrix decompositions.
16
From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure
Researchers developed a multi-agent pipeline based on the Model Context Protocol to convert natural-language documentation into standardized formats for continuous compliance in critical infrastructure.
16
‘Token economy’ emerging as AI use soars in China, experts tell conference
Industry experts in China report that the rapid adoption of artificial intelligence is driving the emergence of a token-based economy for pricing and delivering digital services.
16
一群做自动驾驶的人，盯上了睡眠这件事
Former autonomous driving engineers are applying closed-loop data systems to develop smart sleep technology for bedrooms.
16
好上好：上半年净利润同比预增301.65%—376.03%
Electronic components distributor Hottech predicted its net profit for the first half of 2026 would rise by up to 376.03% year-on-year.
16
《扩大消费“十五五”规划》：优化入境消费环境，稳步扩大免签国家范围
China's State Council has approved the 15th Five-Year Plan for Expanding Consumption, which outlines measures to boost inbound tourism and expand visa-free entry.
16
Huawei’s new computing cluster, world’s first AI agent phone to debut at China AI summit
Huawei plans to debut its next-generation Atlas 950 SuperPoD computing cluster and the world's first AI agent-enabled smartphone at the upcoming World Artificial Intelligence Conference.
16
Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench
A new benchmark called PredicateLongBench has been introduced to systematically analyze the specific factors that make long-context tasks difficult for large language models.
16
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
CausalDS is a new benchmark designed to evaluate the causal reasoning and data analysis capabilities of language model agents.
16
Persona Cartography: Charting Language Model Personality Traits in Weight Space
A new framework maps large language model personality traits within weight space using low-rank adapters to measure and control model personas.
16
Multi-agent Autoformalization of Tensor Network Theory
A new multi-agent workflow utilizing large language models has been developed to autonomously formalize complex theorems in theoretical physics.
16
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Researchers have introduced a proactive memory agent designed to mitigate behavioral state decay in long-horizon tasks by actively retrieving relevant context.
16
Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution
Researchers propose a hierarchical framework that utilizes a centralized large language model for strategic planning to coordinate specialized reinforcement learning policies in multi-agent environments.
16
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
The paper introduces SearchGen-20K and SearchGen-Bench to address the world-knowledge limitations of visual generators by integrating search capabilities.
16
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
The study presents a mechanistic taxonomy and diagnostic pipeline to track how failures like reward hacking and policy collapse emerge during reinforcement learning from human feedback.
16
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
The Large Sparse Reconstruction Model demonstrates how expanding transformer context windows can improve the recovery of fine-grained textures in feed-forward 3D reconstruction.
16
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs
Researchers have introduced Concept-as-Tree, a synthetic data framework designed to improve the personalization capabilities of vision-language models by generating high-quality positive and negative samples.
16
LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis
Researchers developed liteOdyssey, a lightweight framework that guides general-purpose language models through diagnostic reasoning for rare diseases without altering model weights.
16
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
Researchers have introduced ProjAgent, a repository-level code generation system that retrieves functions based on procedural logic rather than simple lexical or semantic similarity.
16
TypeProbe: Recovering Type Representations from Hidden States of Pre-trained Code Models
This study investigates how pre-trained code models internally represent programming types by probing their hidden states across different programming languages.