Hugging Face Trending Papers July 15, 2026

STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle

Read the original on Hugging Face Trending Papers →

LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the final cost cannot say why an agent failed: it may have misread the world, or read it correctly and still failed to act (the knowing-doing gap).

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

arXiv AI

Jul 16

STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle

arXiv:2607. 13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed.

By Sagar Deb, Ashwanth Krishnan

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 30

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

arXiv:2606. 29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review.

By Mengdie Flora Wang, Haochen Xie, Guanghui Wang, Devin Zhang, Jae Oh Woo

llms agents benchmarks safety

arXiv AI

Jul 21

Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.

By Arunabh Dastidar (for the Leni Team)

agents benchmarks

arXiv AI

Jul 7

Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators

arXiv:2607. 04419v1 Announce Type: new Abstract: Most agent evaluations collapse a multi-step trace into a final answer, a success flag, or a trajectory-level score.

By Andrew Zhang, Chengzhan Li

llms agents

arXiv AI

1d ago

No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage

arXiv:2608. 15286v1 Announce Type: cross Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym.

By Shiven Khurdi

llms agents

arXiv AI

Jul 21

Teach it to stop, not just to click

arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.

By Barada Sahu (Cabal AI), Shivesh Pandey (Para AI)

agents reinforcement-learning efficiency multimodal

Related stories

STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

Where Does Agent Reliability Come From? A Cross-Benchmark Decomposition of Verification Loops, Specialist Models, and Scaffolding in a Production Enterprise Agent

Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators

No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage

Teach it to stop, not just to click