thinkbooster 0.1.1

ThinkBooster: a unified framework for test-time compute scaling of LLM reasoning

ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning

Quick Start | Key Features | Strategies | Visual Debugger | Documentation

ThinkBooster is an open-source framework for test-time compute scaling of large language models. It implements nine state-of-the-art scaling strategies — beam search, best-of-N, self-consistency, DeepConf, MUR, phi-decoding, and more — scored by process reward models (PRMs), uncertainty estimators, LLM-as-a-critic, and ReProbes. The framework includes an evaluation pipeline for math, science, and coding benchmarks, an OpenAI-compatible endpoint gateway, and an interactive visual debugger for inspecting strategy behavior step by step.

---

Key Features

• 9 scaling strategies — beam search, best-of-N, self-consistency, DeepConf, MUR, phi-decoding, extended thinking, uncertainty CoT, and adaptive scaling (online and offline)
• 4 scorer families — process reward models (PRMs), uncertainty/confidence scores, LLM-as-a-critic, and ReProbes; with configurable aggregation (min, mean, max, product) and sliding window
• OpenAI-compatible endpoint gateway — drop-in replacement for any OpenAI SDK; select strategy and scorer via URL path; enables "Pro reasoning mode" for any LLM deployment
• Visual debugger — interactive web UI for comparing strategies, inspecting step-by-step reasoning traces and confidence signals
• Evaluation pipeline — math (MATH-500, OlympiadBench, GaoKao, AIME), science (GPQA-Diamond), and coding (HumanEval+, MBPP+, KernelBench) with crash-resistant resume

---

Quick Start

Installation

pip install thinkbooster

Or install from source for development:

git clone https://github.com/IINemo/thinkbooster.git
cd thinkbooster
pip install -e ".[dev]"

Optional: additional scorers (UHead, KernelAct)

Some advanced scorers require GitHub-only dependencies. Run setup.sh after pip install:

./setup.sh

This installs llm-uncertainty-head, vllm-speculators, and KernelAct. Core functionality (all strategies, PRM/entropy/probability scorers, evaluation) works without these.

# Configure API keys (optional, for LLM judge and OpenRouter)
cp .env.example .env

Python API

# Strategies
from thinkbooster.strategies.strategy_baseline import StrategyBaseline
from thinkbooster.strategies.strategy_self_consistency import StrategySelfConsistency
from thinkbooster.strategies.strategy_beam_search import StrategyBeamSearch
from thinkbooster.strategies.strategy_offline_best_of_n import StrategyOfflineBestOfN

# Evaluation utilities
from thinkbooster.evaluation.grader import math_equal
from thinkbooster.evaluation.parser import extract_answer

REST API

git clone https://github.com/IINemo/thinkbooster.git
cd thinkbooster
pip install -e ".[service]"
python service_app/main.py   # starts on http://localhost:8001

Use with any OpenAI SDK:

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8001/v1/beam_search/prm",
    api_key="<YOUR_API_KEY>",
)
response = client.chat.completions.create(
    model="Qwen/Qwen3-30B-A3B",
    messages=[{"role": "user", "content":
        "Find the number of ordered pairs (x, y) of "
        "positive integers satisfying x + 2y = 2xy."}],
    extra_body={
        "max_tokens": 8192, "tts_beam_size": 4,
    },
)
print(response.choices[0].message.content)

The base_url encodes the scaling strategy and scorer (beam_search/prm). To switch strategy, just change the URL — no other code changes needed.

See Service API Guide for the full reference.

Run an Experiment

# Beam search on GSM8K (3 samples for quick verification)
python scripts/run_tts_eval.py \
  --config-name experiments/beam_search/gsm8k/window_all/mean/beam_search_vllm_qwen25_math_7b_instruct_gsm8k_prm \
  dataset.subset=3

Results are saved to outputs/ with full config snapshots for reproducibility. Add --resume to continue interrupted runs.

---

Visual Debugger

The interactive debugger lets you compare multiple TTS strategies side by side on the same problem. Inspect per-step decisions (escalate, stop, prune, select), view confidence and uncertainty signals, and drill into sampled candidates and tree expansions.

	Main interface. Select a cached example or enter a custom math/science/coding problem. Choose any strategy (beam search, best-of-N, MUR, …) and scorer (PRM, uncertainty, LLM-as-a-critic) and run it directly from the browser.
	Step inspector. Replay the strategy execution step by step. Each entry in the reasoning timeline shows the operation (select, prune, escalate), the candidates considered, their scores, and the full text of the chosen step.
	Trajectory tree. Global branching view of the entire strategy run. Nodes represent reasoning steps; the orange path highlights the final selected trajectory. Useful for understanding how beam search or tree-of-thought explores and prunes the search space.

After starting the REST API service, open:

http://localhost:8001/debugger

See service_app/README.md for details on cached examples and custom input modes.

---

Supported Strategies

Strategy	Online/Offline	LLM Access	Prefill	Description
Best-of-N	Offline	Black-box	No	Sample N solutions, select best by scorer
Majority Voting	Offline	Black-box	No	Sample N solutions, select answer by majority vote
Beam Search (ToT)	Online	Black-box	Yes	Explore tree of reasoning paths, prune by score
Extended Thinking	Online	Black-box	Yes	Control reasoning budget to force longer CoT
MUR	Online	White-box	Yes	Allocate more compute only on uncertain steps
DeepConf Online	Online	White-box	Yes	Steer generation toward high-confidence tokens
DeepConf Offline	Offline	White-box	No	Rerank candidates by model confidence scores
Phi-decoding	Online	White-box	Yes	Foresight sampling and adaptive pruning
Uncertainty CoT	Online	White-box	Yes	Generate multiple trajectories when uncertain

---

Project Structure

thinkbooster/
├── thinkbooster/         # Core library (pip install thinkbooster)
│   ├── strategies/       # TTS strategy implementations
│   ├── models/           # Model wrappers (vLLM, HuggingFace, API)
│   ├── scorers/          # Step scoring (PRM, uncertainty, voting)
│   ├── evaluation/       # Correctness evaluation (exact match, LLM judge)
│   └── datasets/         # Dataset loaders and utilities
├── config/               # Hydra configuration system
├── scripts/              # Evaluation scripts (run_tts_eval.py)
├── service_app/          # REST API service + visual debugger
├── tests/                # Test suite with strategy registry
├── docs/                 # Documentation
└── setup.sh              # Optional: install GitHub-only deps (UHead, KernelAct)

See Project Structure for a detailed architecture overview.

---

Documentation

• Project Structure — architecture and component descriptions
• Evaluation Protocol — datasets, metrics (accuracy, tokens, FLOPs), and reporting
• Strategy Registration — how to add new strategies with tests
• Service API Guide — REST API reference and configuration
• DeepConf Guide — confidence-based test-time scaling

---

Contributing

We welcome contributions! Whether it's a new strategy, scorer, dataset, or bug fix — see the Contributing Guide for setup instructions, development workflow, and coding standards.

---

Citation

If you use ThinkBooster in your research, please cite:

@misc{thinkbooster2026,
  title     = {ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning},
  author    = {Smirnov, Vladislav and Nguyen, Chieu and Senichev, Sergey and Ta, Minh Ngoc and Fadeeva, Ekaterina and Vazhentsev, Artem and Galimzianova, Daria and Rozanov, Nikolai and Mazanov, Viktor and Ni, Jingwei and Wu, Tianyi and Kiselev, Igor and Sachan, Mrinmaya and Gurevych, Iryna and Nakov, Preslav and Baldwin, Timothy and Shelmanov, Artem},
  booktitle = {Preprint},
  year      = {2026},
  url       = {https://thinkbooster.s3.us-east-1.amazonaws.com/thinkbooster.pdf}
}

---

Troubleshooting

vLLM engine fails to start

Corrupted torch compile cache: If you see RuntimeError: Engine core initialization failed:

rm -rf ~/.cache/vllm/torch_compile_cache/

Missing C compiler: If Triton can't find gcc:

conda install -c conda-forge gcc_linux-64 gxx_linux-64 -y
ln -s $CONDA_PREFIX/bin/x86_64-conda-linux-gnu-gcc $CONDA_PREFIX/bin/gcc
ln -s $CONDA_PREFIX/bin/x86_64-conda-linux-gnu-g++ $CONDA_PREFIX/bin/g++

ANTLR version mismatch warnings

ANTLR runtime and generated code versions disagree: 4.9.3!=4.7.2

This is expected — Hydra uses ANTLR 4.9.3, latex2sympy2 was built with 4.7.2. Both work correctly.

---

License

This project is licensed under the MIT License — see the LICENSE file for details.