test-time-compute

Implement a reasoning LLM in PyTorch from scratch, step by step

Repo for AI Agents The Definitive Guide

Inference-time scaling for LLMs-as-a-judge.

Multi-agent demo platform for Titans (arXiv:2501.00663) — neural networks that learn to memorize at test time. 7 AI agents, native desktop UI.

Official repository of the spotlight ICML 2025 paper, PokeChamp: an Expert-level Minimax Language Agent.

[NeurIPS 2026] State of Thought Enables Endogenous Reasoning

Compound model panel for pi: parallel model calls, then one synthesis response.

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

Hardware-aligned latent deliberation framework decoupling System 2 continuous reasoning from System 1 autoregressive decoding.

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

[NeurIPS 2025 Spotlight] Official implementation of "Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting"

Evolving agent harnesses: a research program on how far N orchestrated calls of a small model can rival a frontier model. We evolve the harness (structure + prompts) with reflective optimizers + a verified-acceptance gate.

Test-Time Memory Framework: Control Hallucinations in Foundation Models

A bilingual atlas of looped and recursive Transformers, latent reasoning, and test-time compute. 持续更新的 Loop Transformer 双语研究图谱。

Awesome list of papers, code, models and blogs on Looped / recurrent-depth / weight-tied Transformers — depth as a third scaling axis

Tree execution engine for LLM inference: fork, merge, prune KV cache at token granularity

Official implementation of Dynamic Parallel Tree Search for accelerating LLM reasoning with test-time parallel search.

Turn LLM coding agents (Claude Code, Codex) from next-token predictors into divergent thinkers. A research-grounded cognitive engine + drop-in Claude Code skills for creativity, reasoning & robustness, with 6 honest reproducible benchmarks and 137 verified papers.

Code for the paper "Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement"

Awesome list + deep-dive reports on looped / recurrent-depth transformers (2018-2026): the Loop technology behind GPT-6 Astra. 122 papers, ZH/EN reports, translated PDFs, survey, slides.