iiis-ai / cumulative-reasoning
Official implementation of paper "Cumulative Reasoning With Large Language Models" (https://arxiv.org/abs/2308.04371)
☆293Updated 8 months ago
Alternatives and similar repositories for cumulative-reasoning
Users that are interested in cumulative-reasoning are comparing it to the libraries listed below
Sorting:
- FireAct: Toward Language Agent Fine-tuning☆275Updated last year
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆314Updated 11 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆261Updated 8 months ago
- Data and Code for Program of Thoughts (TMLR 2023)☆272Updated last year
- [ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning☆223Updated 4 months ago
- Generative Judge for Evaluating Alignment☆237Updated last year
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)☆262Updated last year
- Paper collection on building and evaluating language model agents via executable language grounding☆355Updated last year
- papers related to LLM-agent that published on top conferences☆315Updated last month
- ☆328Updated 3 months ago
- MAD: The first work to explore Multi-Agent Debate with Large Language Models :D☆374Updated 4 months ago
- A new tool learning benchmark aiming at well-balanced stability and reality, based on ToolBench.☆149Updated last month
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆309Updated 9 months ago
- ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels …☆261Updated last year
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆308Updated 6 months ago
- Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"☆281Updated 6 months ago
- ☆280Updated 9 months ago
- Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" [ICLR 2024]☆370Updated 8 months ago
- This is the official implementation of "Progressive-Hint Prompting Improves Reasoning in Large Language Models"☆206Updated last year
- Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Langu…☆347Updated last year
- ☆121Updated 11 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆554Updated 5 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆338Updated last year
- RewardBench: the first evaluation tool for reward models.☆566Updated last week
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆304Updated 8 months ago
- Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)☆205Updated 2 years ago
- ☆135Updated 4 months ago
- Large Language Models Are Reasoning Teachers (ACL 2023)☆335Updated 2 months ago
- ToolBench, an evaluation suite for LLM tool manipulation capabilities.☆151Updated last year
- Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)☆139Updated 6 months ago