lechmazur / pactLinks
A benchmark for conversational bargaining by language models. In each 20‑round match one LLM plays buyer, one plays seller, and both hold a hidden private value. Every round they swap a short public message, then post a bid or ask; a deal clears whenever the bid meets the ask.
☆33Updated 5 months ago
Alternatives and similar repositories for pact
Users that are interested in pact are comparing it to the libraries listed below
Sorting:
- Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs☆24Updated 7 months ago
- ☆37Updated 6 months ago
- Pivotal Token Search☆145Updated last month
- A mcp server that uses the Osmosis-Apply-1.7B model to apply code merges☆53Updated 7 months ago
- Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…☆27Updated 8 months ago
- Train an adapter for any embedding model in under a minute☆130Updated 10 months ago
- XmodelLM☆38Updated last year
- Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)☆115Updated last week
- synthetic dataset generation workflow using local file resources for finetuning llms.☆82Updated 4 months ago
- Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)☆47Updated this week
- Digital Red Queen: Adversarial Program Evolution in Core War with LLMs☆176Updated 3 weeks ago
- ☆107Updated 3 months ago
- ☆63Updated 7 months ago
- Efficient non-uniform quantization with GPTQ for GGUF☆58Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 3 months ago
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?☆259Updated last month
- Code for WALT – Web Agents that Learn Tools☆63Updated 3 months ago
- ☆20Updated 11 months ago
- Training Proactive and Personalized LLM Agents☆100Updated 3 weeks ago
- powerful and fast tool calling agents☆80Updated 10 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structure☆52Updated last year
- ☆100Updated 8 months ago
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆23Updated 7 months ago
- ☆30Updated last year
- Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and…☆50Updated 8 months ago
- a Python library that uses Reinforcement Learning (RL) to train LLMs.☆42Updated 6 months ago
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated last year
- LLMProc: Unix-inspired runtime that treats LLMs as processes.☆34Updated 6 months ago
- ☆50Updated 2 months ago
- Editor with LLM generation tree exploration☆84Updated last year