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.

Official code for "Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration" (SOE, ACL 2026 Oral). A training-free, test-time scaling method that fixes reasoning collapse in LLM mathematical reasoning via orthogonal probing.

[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

ICLR 2026 code for Echoes as Anchors: why large reasoning models restate the question in long chain-of-thought. Echo-Distilled SFT, training-free Echoic Prompting (test-time compute), echo likelihood gap and attention analysis on math reasoning (GSM8K, MATH, AIME24).

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"

LLM reasoning: use draft agreement to route queries and allocate adaptive thinking budgets without training.

235 papers on looped and recursive Transformers, latent reasoning, and test-time compute. Bilingual EN/ZH atlas with official code and summaries. 持续更新的 Loop Transformer 研究图谱。

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.

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.

Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals

Test-Time Memory Framework: Control Hallucinations in Foundation Models

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

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.