multi-turn-reasoning

Here are 4 public repositories matching this topic...

OpenMLRL / CoMLRL

Open-Source Library for Fully Cooperative Multi-LLM Reinforcement Learning

research multi-agent-systems multi-agent-reinforcement-learning marl mappo multi-llm multi-turn-reasoning llm-collaboration multi-llm-colaboration magrpo comlrl openmlrl

Updated Sep 7, 2026
Python

xzx34 / SocialMaze

Star

EMNLP 2026 Findings benchmark for LLM social reasoning across dynamic interaction, social deduction, deception, and information uncertainty; maintained HRD code and data.

deception theory-of-mind social-deduction social-intelligence social-reasoning llm-evaluation multi-turn-reasoning dynamic-interaction emnlp-2026 language-model-benchmark hidden-role-deduction information-uncertainty

Updated Sep 21, 2026
Python

MitchBaba / Drift-Tag

Star

Structured behavioral labeling and trust-curve analysis for replay-faithful AI conversation logs.

dialogue-systems ai-safety conversational-ai multi-turn-dialogue llm-evaluation llm-observability multi-turn-reasoning ai-red-teaming dataset-processing trust-modeling multi-turn-conversations

Updated Jul 7, 2026

Benchmark and evaluation code for the ICLR 2026 Workshop paper 'Residual Drift Dominates Contradiction in Multi-Turn Constraint Reasoning'. 1,020 Z3-validated multi-turn constraint problems across seating, scheduling, and logic-grid domains.

benchmark z3 constraint-satisfaction reasoning workshop-paper llm llm-evaluation multi-turn-reasoning llm-benchmark iclr2026 satisfiable-drift minimal-unsatisfiable-subset reasoning-and-planning

Updated Apr 25, 2026
Python

Add this topic to your repo

To associate your repository with the multi-turn-reasoning topic, visit your repo's landing page and select "manage topics."

Learn more

Navigation Menu