Alternatives and similar repositories for MathBlackBox

Users that are interested in MathBlackBox are comparing it to the libraries listed below

• HarleyCoops / smolThinker-.5B
  A Qwen .5B reasoning model trained on OpenR1-Math-220k
  ☆14Updated 6 months ago
• convergence-ai / webgames
  Challenges for general-purpose web-browsing AI agents
  ☆64Updated 3 months ago
• google-deepmind / latent-multi-hop-reasoning
  [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?
  ☆77Updated 5 months ago
• allenai / clin
  ☆86Updated last year
• SalesforceAIResearch / LaTRO
  ☆122Updated 6 months ago
• agentification / RAFA_code
  ☆144Updated last year
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆96Updated 2 weeks ago
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆150Updated 7 months ago
• allenai / genesys
  Source code and utilities for the Genesys distributed language model architecture discovery system.
  ☆49Updated 2 months ago
• archiki / ADaPT
  Official code for the paper "ADaPT: As-Needed Decomposition and Planning with Language Models"
  ☆89Updated last year
• sunblaze-ucb / AgentSynth
  AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
  ☆31Updated 2 weeks ago
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆182Updated 6 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆172Updated 8 months ago
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆105Updated 3 months ago
• gkamradt / SnakeBench
  ☆90Updated 3 months ago
• benpry / why-think-step-by-step
  Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"
  ☆61Updated 5 months ago
• siyuyuan / evoagent
  Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"
  ☆124Updated 10 months ago
• Danau5tin / calculator_agent_rl
  Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
  ☆49Updated 4 months ago
• Xalp / ECHO
  Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)
  ☆92Updated 7 months ago
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆105Updated last month
• Wenyueh / game_theory
  How to create rational LLM-based agents? Using game-theoretic workflows!
  ☆74Updated 3 months ago
• portal-cornell / muCode
  ☆19Updated 2 months ago
• brendanhogan / completion_tree_view
  ☆13Updated 4 months ago
• Aloriosa / srmt
  The original Shared Recurrent Memory Transformer implementation
  ☆31Updated 2 months ago
• conglu1997 / intelligent-go-explore
  Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models
  ☆64Updated 6 months ago
• yueqis / API-Based-Agent
  ☆56Updated 2 months ago
• jinhaoduan / GTBench
  [NeurIPS 2024] GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
  ☆66Updated last year
• gabegrand / lilo
  LILO: Library Induction with Language Observations
  ☆88Updated last year
• oriyor / assistantbench
  Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"
  ☆62Updated 9 months ago
• agiresearch / Formal-LLM
  Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
  ☆127Updated last year