Hugging Face Trending Papers June 22, 2026

On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners

Read the original on Hugging Face Trending Papers →

Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: language is a compressed and capacity-limited interface for conveying task information.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

1d ago

CAPO: Constraint-Aware Prompt Optimization for LLM Agents

arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.

By Victor Ye Dong, Reid Pryzant, Yi Liu, Jian Jiao

llms agents benchmarks safety

arXiv AI

Jul 24

FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts

arXiv:2607. 20500v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer.

By Sizhe Tang, Guangyu Jiang, Yu Li, Rongqian Chen, Ioannis G. Kevrekidis, Tian Lan

llms rag

arXiv AI

Aug 10

Ask-E: An Environment for Calibrated Question Generation

arXiv:2608. 06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.

By Sarah Pratt, Jae Sung Park, Scott Geng, Ali Farhadi

llms benchmarks

arXiv AI

5d ago

Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction

arXiv:2608. 12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, output schemas.

By Mariya I. Vasileva

llms benchmarks safety

arXiv AI

Jul 24

Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solving

arXiv:2607. 20520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical problem solving, yet prior work often treats representationally equivalent formulations as interchangeable and conflates reasoning errors with interface failures.

By Sagnik Nath, Edith Aurora Graf, Liang Zhang, Diego Zapata-Rivera

llms

arXiv AI

1d ago

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

arXiv:2602. 15983v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations---a feasibility--correctness gap reaching 90 percentage points on compositional problems.

By Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo

llms fine-tuning benchmarks

Related stories

CAPO: Constraint-Aware Prompt Optimization for LLM Agents

FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts

Ask-E: An Environment for Calibrated Question Generation

Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction

Representation Robustness Under Executable Reasoning Constraints in Large Language Models for Mathematical Problem Solving

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization