nexusflowai / NexusBenchLinks
Nexusflow function call, tool use, and agent benchmarks.
☆30Updated last year
Alternatives and similar repositories for NexusBench
Users that are interested in NexusBench are comparing it to the libraries listed below
Sorting:
- ☆55Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 2 months ago
- ☆63Updated 5 months ago
- ☆19Updated 9 months ago
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆33Updated 3 months ago
- entropix style sampling + GUI☆27Updated last year
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated last year
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 11 months ago
- Jina VDR is a multilingual, multi-domain benchmark for visual document retrieval☆37Updated 4 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆66Updated last year
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆84Updated 9 months ago
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents☆35Updated 2 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆97Updated 7 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆100Updated 3 months ago
- Verifiers for LLM Reinforcement Learning☆80Updated 8 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Updated 2 months ago
- ☆68Updated 7 months ago
- ☆27Updated last month
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆26Updated last week
- ☆40Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- THOUGHTSCULPT, a general reasoning and search method for complex tasks☆13Updated last year
- ☆52Updated last year
- ☆32Updated last year
- This repository contains the code for the paper: SirLLM: Streaming Infinite Retentive LLM☆60Updated last year
- Simple examples using Argilla tools to build AI☆57Updated last year
- ☆68Updated last year
- Lego for GRPO☆30Updated 6 months ago
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Models☆115Updated 8 months ago