Fudan Researchers Find 1-in-10 MCP Tools Lie to AI Agents
A new study scanned 2,214 real-world MCP servers and found nearly 1-in-10 tools lie to the AI agents that use them
20 stories
A new study scanned 2,214 real-world MCP servers and found nearly 1-in-10 tools lie to the AI agents that use them
NoRA is a new video benchmark that tests whether AI agents can justify social actions from first-person video, not just pick from a menu of choices
A new precision controller for physics-informed neural networks dynamically switches between FP32 and FP64 using curvature signals, matching full double-precision accuracy at lower compute cost.
TIDE is a new agent framework from KAIST that proactively hunts down multiple hidden problems in your documents and code — without being asked
VISTA fixes the two core reasons UMI robot data fails to train large VLA models: distorted fisheye vision and physically impossible human trajectories
A 1.6M-parameter Box Predictor module turns a single click into a bounding box, dramatically improving MedSAM segmentation across CT, MRI, and ultrasound
MC-GLM adds calibrated uncertainty estimates to any trained 3D object detector without retraining, a critical step for safe autonomous driving deployment.
A new paper finally explains why Muon trains LLMs 2x faster than Adam -- the answer lies in how each optimizer navigates the curvature of the loss landscape
BiNSGPS adds a feedback loop between a vision-language model and a symbolic solver, hitting 95.7% on MathVista's geometry benchmark
A new reproducibility study of Vul-RAG finds the framework works without proprietary APIs, but every open-weight model tested, including reasoning models, hits a hard ceiling of ~0.30 pairwise accuracy on vulnerability detection.
CTDG-SSM fuses HiPPO memory with graph Laplacian polynomials to achieve state-of-the-art on dynamic link prediction with 10x fewer parameters than competitors
MIRAGE teaches mobile AI agents to reason silently in compressed hidden states, cutting token output by 75% while matching or beating chain-of-thought baselines on real Android tasks
Multi-SPIN turns every user's phone into a draft engine, boosting edge LLM token throughput by up to 88% through smart bandwidth and draft-length co-optimization.
Ekka is a new agentic system that automatically pinpoints the root cause of silent quality regressions in LLM serving frameworks like vLLM and SGLang, achieving 80% accuracy at ICML 2026.
Sci-PRM brings step-by-step reasoning verification to biology, chemistry, and physics by teaching reward models to evaluate tool use, not just logic
Parthenon introduces a self-improving legal agent framework that learns from its own failures without retraining, tested across 12,510 agent trajectories on Harvey's LAB benchmark
QuBLAST assigns different bit-widths to each transformer block using cross-entropy sensitivity, shrinking 8B models by up to 45% with under 5% quality loss
DMAIC-IAD borrows a Six Sigma quality framework to give LLM agents a structured plan before running industrial defect detection, beating baselines by 37.76%
SegTreeMem organizes conversation history as a chronologically ordered tree, beating flat retrieval and graph memory by up to 20% on long-horizon QA benchmarks.
Baidu's MapAgent uses a Judge-Planner-Worker agent loop to fix lane-map errors at scale, pushing production automation past 95% across 360+ cities