SURL AI News
繁中English日本語

Archive

All News

1540 technical news articles

硬體

SAT-Edge-Agent Tests a Satellite Edge Agent, with Object Detection Accounting for Only About 2.5% of End-to-End Latency

SAT-Edge-Agent integrates a local language service and an oriented object detector on a commercial heterogeneous ARM SoC, completing all 40 runs of a fixed workload. Measurements show that most latency comes not from the vision model but from agent orchestration and the language service, although the study did not evaluate detection accuracy, power consumption, or flight reliability.
代理工具

TARL Splits Agent Memory Updates Into Five Transaction Types, Raising Next-State Accuracy to 66.21%

Rather than managing agent memory as a binary “write or hold” decision, TARL explicitly distinguishes among appending, ignoring, revising, rejecting conflicts, and deferring for verification. The authors’ experiments show that the memory contamination rate fell to 25.24%, but the model and dataset are currently available only through the paper’s supplementary materials.
AI 安全

LatentGuard Compresses Safety Reasoning into Continuous States, Cutting the Critical Path from 268.56 Text Tokens to 1.60

Rather than generating a complete safety rationale for every review, LatentGuard uses staged training to compress rationales into a small number of latent states and output decisions directly. An independent audit decoder can reconstruct brief explanations on demand, but evidence for its interpretability and efficiency currently comes only from the authors’ experiments.
代理工具

ContinualSkillBench Finds That Most Progress in Agents’ “Accumulated Skills” Can Be Explained by Contextual Adaptation

ContinualSkillBench evaluates whether agents can organize experience into reusable skills using five domains, each containing 100 progressively dependent tasks. Explicit skill libraries did not significantly outperform simply retaining context on average, showing that growth in the number of skills does not by itself prove that an agent is capable of continual learning.
最新模型

ReflectRL Turns Expert Error Trajectories into Training Signals, Improving GRPO Cross-Domain Evaluation by an Average of 19.1 Points

Instead of discarding reasoning trajectories where a strong model produces an incorrect answer, ReflectRL asks the student model to identify localized errors and then gradually removes this hint. The study reports consistent gains across nine benchmarks, although the results come primarily from mathematical reasoning settings, and the listed GitHub project link is currently inaccessible.
AI 安全

Science Reasoning Benchmark Shows “Right Answer, Wrong Method,” With Shortcut Solutions Reaching 37.4% on HLE

A new study finds that models can obtain correct results without completing the required derivation by using shortcuts such as guessing formulas, enumeration, or guessing an answer first and then verifying it. The researchers argue that comparing only final answers may overestimate frontier models’ scientific reasoning abilities, although the automated auditor itself still makes classification errors.
最新模型

Faster-WAM Shrinks the Robot Action Head to a Single Layer, Cutting Control Inference Latency to 66.5 Milliseconds

Faster-WAM attaches a single-layer action head to a 30-layer video Transformer and obtains world-model representations through cross-layer KV fusion, eliminating the need for the action branch to replicate the full backbone depth. The study reports a 3.2× speedup over Fast-WAM, but code and weights for the new architecture have not yet been released, and the results come primarily from simulation benchmarks.