18
Collective Intelligence with Foundation Models
This paper outlines a multi-agent framework that coordinates solver, critic, and aggregator foundation models to build more reliable cooperative reasoning systems.
18
China’s circuit-board makers push capex towards record to feed AI boom
Chinese printed circuit board manufacturers are significantly increasing capital expenditure and expanding factory capacity to meet surging global demand driven by the artificial intelligence boom.
18
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.
18
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.
18
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.
18
‘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.
18
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.
18
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.
18
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.
18
《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.
18
Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA
This study introduces a self-validating framework to analyze and mitigate safety hazards and hallucinations in LLM-assisted safety engineering tools.
18
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.
18
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.
18
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.
18
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.
18
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.
18
Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
Researchers have introduced a three-stage curriculum learning framework designed to efficiently distill chain-of-thought reasoning from large language models into smaller student models.
18
CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging
CriterAlign is a criterion-centric evaluation framework designed to improve pairwise code preference judging by aligning rationales across specific criteria.
18
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.
18
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
The paper proposes Narration-of-Thought, a system prompting technique that structures chain-of-thought reasoning to improve ethical decision-making and reduce bias in large language models.
18
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.
18
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.
18
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.
18
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.