专题｜RSI 与 Agent 自进化：站内内容地图与三条阅读路线
本站「RSI 与 Agent 自进化」专题入口页：把站内 11 篇原创深度与 14 条一手动态收进同一张地图——先给 30 秒定性（RSI 改"改进能力"、自进化改"任务表现"），再按概念／全景／证据／判定／事件／工程／治理七层分层索引，附三条按时间预算划分的阅读路线（30 分钟 / 2 小时 / 半天）、一页速查卡、收录标准与更新日志。
阅读全文 →
全部文章
ARCHIVE 共 470 条Revisiting Complete Reasoning Traces for Post-Training
Large language models (LLMs) are often post-trained on pre-collected reasoning trajectories to improve their reasoning c…
Reason Through the Latent! Making Latent Visual Reasoning Necessary
Latent visual reasoning aims to perform multimodal reasoning through hidden-state computation rather than explicit textu…
VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification
Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question …
Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts
Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-mo…
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing b…
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal deco…
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers prov…
Last Translation Benchmark
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that…
Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles
Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point toleranc…
TempCloze: Can Video-LLMs Identify the Missing Middle?
Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from …
诺贝尔物理学奖授予神经网络先驱 Hopfield 与 Hinton
2024 年诺贝尔物理学奖授予 John Hopfield 与 Geoffrey Hinton，表彰其利用人工神经网络实现机器学习的基础性发现；化学奖同时颁给蛋白质计算先驱。