Papers we read over April 01 - April 07

🤔 Reasoning & Planning

📜 Paper	🔗 Resources
Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning (NAACL'24)	code
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks (NAACL'24)	code
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models
FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs (NAACL'24)
Demystifying Chains, Trees, and Graphs of Thoughts
Advancing LLM Reasoning Generalists with Preference Trees	tweet, code, collection
Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models	tweet, code
Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos (CVPR'24)	code

📜 Paper	🔗 Resources
Planning and Editing What You Retrieve for Enhanced Tool Learning (NAACL'24)	tweet, code
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (NAACL'24)	code

📜 Paper	🔗 Resources
Language Models are Spacecraft Operators	code

📜 Paper	🔗 Resources
LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models (LLMAgents Workshop @ ICLR'24)	code, website
OpenAgents: An Open Platform for Language Agents in the Wild (LLMAgents Workshop @ ICLR'24)
Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization	code
JetMoE: Reaching Llama2 Performance with 0.1M Dollars	code, website, model