LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

arXiv:2601.06973 · cs.CL · Submitted 2026-01-11 · Read on arXiv

cs.CL

Submitted: 2026-01-11

Updated: 2026-09-02

Code: https://github.com/chandar-lab/Hangman

Terminology

• Consistency — 44× in this paper · explained in 3 episodes
• Self-consistency — 16× in this paper · explained in 2 episodes
• Trace — 16× in this paper · explained in 2 episodes
• Private State Interactive Task — 11× in this paper
• Reasoning Traces — 6× in this paper · explained in 3 episodes
• Agent Architectures — 5× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• RAG — 5× in this paper · explained in 3 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Public-Only Chat Agent — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Agentic Framework — 2× in this paper · explained in 6 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Private Chain-of-Thought — 2× in this paper
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic Memory System — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• gpt-oss-120b & gpt-oss-20b Model Card
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Eliciting Reasoning in Language Models with Cognitive Tools
• LightMem: Lightweight and Efficient Memory-Augmented Generation
• HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
• Unified Mind Model: Reimagining Autonomous Agents in the LLM Era
• Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
• Deep Research Agents: A Systematic Examination And Roadmap
• Why Language Models Hallucinate
• Memory OS of AI Agent
• Unlocking Structured Thinking in Language Models with Cognitive Prompting
• MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
• StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
• On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering