Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Baldelli, Davide, Parviz, Ali, Zouaq, Amal, Chandar, Sarath
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probabilistic Calibration Is a Trainable Capability in Language Models
by: Baldelli, Davide, et al.
Published: (2026)

Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval
by: Sharma, Aditya, et al.
Published: (2025)

A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
by: Thakkar, Megh, et al.
Published: (2024)

What is the Best Process Model Representation? A Comparative Analysis for Process Modeling with Large Language Models
by: Brissard, Alexis, et al.
Published: (2025)

Ontology-Constrained Generation of Domain-Specific Clinical Summaries
by: Mehenni, Gaya, et al.
Published: (2024)

Faithfulness Measurable Masked Language Models
by: Madsen, Andreas, et al.
Published: (2023)

CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
by: Govindarajan, Prashant, et al.
Published: (2025)

Are self-explanations from Large Language Models faithful?
by: Madsen, Andreas, et al.
Published: (2024)

Towards Practical Tool Usage for Continually Learning LLMs
by: Huang, Jerry, et al.
Published: (2024)

A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questions
by: Diallo, Papa Abdou Karim Karou, et al.
Published: (2023)

FRASE: Structured Representations for Generalizable SPARQL Query Generation
by: Diallo, Papa Abdou Karim Karou, et al.
Published: (2025)

Enhancing Frame Detection with Retrieval Augmented Generation
by: Diallo, Papa Abdou Karim Karou, et al.
Published: (2025)

GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models
by: Sharma, Aditya, et al.
Published: (2024)

Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
by: Prato, Gabriele, et al.
Published: (2025)

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions
by: Song, Maojia, et al.
Published: (2025)

EpiK-Eval: Evaluation for Language Models as Epistemic Models
by: Prato, Gabriele, et al.
Published: (2023)

Interpretability Needs a New Paradigm
by: Madsen, Andreas, et al.
Published: (2024)

AbsenceBench: Language Models Can't Tell What's Missing
by: Fu, Harvey Yiyun, et al.
Published: (2025)

Do Large Language Models Know How Much They Know?
by: Prato, Gabriele, et al.
Published: (2025)

DeSQ: Decomposition-based SPARQL Query Generation
by: Diallo, Papa Abdou Karim Karou, et al.
Published: (2026)

Why Don't Prompt-Based Fairness Metrics Correlate?
by: Zayed, Abdelrahman, et al.
Published: (2024)

Should We Attend More or Less? Modulating Attention for Fairness
by: Zayed, Abdelrahman, et al.
Published: (2023)

You Can't Fight in Here! This is BBS!
by: Futrell, Richard, et al.
Published: (2026)

"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
by: Halevy, Karina, et al.
Published: (2024)

Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
by: Thakkar, Megh, et al.
Published: (2024)

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
by: Sun, Yiyou, et al.
Published: (2025)

Small Encoders Can Rival Large Decoders in Detecting Groundedness
by: Abbes, Istabrak, et al.
Published: (2025)

NeuroFaith: Evaluating LLM Self-Explanation Faithfulness via Internal Representation Alignment
by: Bhan, Milan, et al.
Published: (2025)

Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
by: Wang, Wenxuan, et al.
Published: (2025)

MedHal: An Evaluation Dataset for Medical Hallucination Detection
by: Mehenni, Gaya, et al.
Published: (2025)

Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
by: Kamath, Amita, et al.
Published: (2026)

LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench
by: Valmeekam, Karthik, et al.
Published: (2024)

Can't say cant? Measuring and Reasoning of Dark Jargons in Large Language Models
by: Ji, Xu, et al.
Published: (2024)

Semantic Deception: When Reasoning Models Can't Compute an Addition
by: de Leeuw, Nathaniël, et al.
Published: (2025)

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination
by: Huang, Jerry, et al.
Published: (2024)

Empowering Working Memory for Large Language Model Agents
by: Guo, Jing, et al.
Published: (2023)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
by: Cao, Bochuan, et al.
Published: (2025)

Too Big to Fool: Resisting Deception in Language Models
by: Samsami, Mohammad Reza, et al.
Published: (2024)

Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?
by: Balepur, Nishant, et al.
Published: (2024)

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
by: Prakash, Nirmalendu, et al.
Published: (2025)