Hugging Face Trending Papers

What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents

arXiv AI
Oct 1

What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents

The article reviews how replacing components in language‑model agents affects execution trajectories and downstream outcomes. It maps 348 studies, analyzes 90 comparison records, and finds that while many studies report both local decision metrics and task endpoints, they rarely demonstrate matched comparisons or prove that improved local decisions drive task‑level gains. The review identifies three potential mechanisms—recovery and disruption, intervention timing, and downstream use—and proposes eight claim‑specific reporting items to clarify evidence quality.

By Shuyang Zhang (The Hong Kong Polytechnic University), Jianshuo Chang (The Hong Kong Polytechnic University)
arXiv AI
Oct 16

What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports

The paper introduces CTXGAP, a study measuring how much information coding agents omit from their user-facing reports compared to their full execution logs. Across 37 coding tasks, agents answer 93.6% of task-state questions when asked directly, but report-only readers recover only 52.0% of the same information, revealing a 40.7‑point gap. Even at final checkpoints of verified fixes, the gap remains significant, and detailed terminal scrollback improves recovery only to 73.6%. The study highlights that missing details in reports can leave supervisors unaware of failures, workarounds, and risks that need scrutiny.

By Guoyang Xu, Rui Zhang, Xiuyu Wu, Hao Chen
arXiv AI
Oct 1

NAQD Env: A benchmark for selective withdrawal in language agents

The paper introduces NAQD‑Env, a synthetic benchmark designed to test language agents’ ability to selectively withdraw and resume actions when new evidence, permissions, or stop instructions arise. It evaluates models against a deterministic reference policy across eleven dependency families, measuring policy agreement, task value, withdrawal, resumption, and event reporting. Experiments on 350 scenarios show low withdrawal recall, no valid resumption, and limited policy alignment, highlighting the need to treat selective withdrawal as a distinct reliability component.

By Mohamed Abouzahra
arXiv Machine Learning
Sep 30

Frozen Judges, Moving Agents: Version-Dependent LLM-Judge Error and the Limits of Judge-Assisted Agent Evaluation

The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.

By Jiapeng Li
arXiv AI
Oct 28

Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors

The paper argues that classification accuracy alone is insufficient for evaluating AI agent restart monitors. It introduces a decision‑value framework with a decision‑sufficiency criterion and a finite‑sample decision audit to assess whether restarting an agent is beneficial. Empirical results on SymPy issues show that high accuracy can lead to both gains and losses, and that many traces fail to meet the audit’s certification threshold.

By Siddharth Jain, Venkat N. Vedam
arXiv AI
Oct 16

From Migration to Calibration: Aligning Agents with Deployment Requirements

The paper proposes a framework for aligning AI agents with deployment requirements through a process called calibration, which avoids the need for source imitation or universal superiority. It introduces three families of requirements—basic capability, technical precision, and user context—alongside a versioned mapping to manage changes. The authors outline four instruments (benchmarks, examples, skills, and role-conditioned cost/utility) that provide tunable reward channels within a fixed acceptance contract, and describe methods for adaptation, qualification, and evaluation, noting that confirmatory validation remains outstanding.

By Yaxiao Liu (PwC China AI Center), Pengbo Liu (PwC China AI Center), Yiwen Liu (PwC China AI Center), Yihua Guan (PwC China AI Center), Jiaxing Song (Tsinghua University), Xingjian Li (PwC China AI Center)
arXiv AI
Aug 28

Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistency

The study compared human and large language model (LLM) workflows for title‑and‑abstract screening in a complex scoping review. Human reviewers and two GPT‑5.4 file‑batch runs retained 42.2‑45.0% of records with 82.3‑82.9% recall, while Gemini 3.1 achieved the highest recall (83.9%) but retained 56.7% of records. Identical GPT‑5.4 runs showed 91.7% agreement yet differed on 94 records, including 29 verified eligible ones.

By Nikol Figalov\'a, Lynn Huestegge, Anne B\"ockler-Raettig
arXiv Computation and Language
Oct 9

TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation

The paper introduces TRACE, a protocol designed to diagnose whether changes in verifier scores for large language model agents reflect actual changes in agent behavior or merely alterations in the evaluation process. TRACE works by applying targeted changes to evaluation components, running paired experiments, and re‑scoring unchanged trajectories to isolate the source of score variation. Experiments on synthetic tasks and public benchmark tasks demonstrate that seemingly significant score shifts can often be attributed to evaluation artifacts, while TRACE can also detect genuine behavioral changes.

By Radhika Gaonkar
arXiv AI
Oct 16

Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language Agents

The paper investigates how fine‑tuned language agents can selectively withdraw actions when evidence changes or authority is revoked. Using a synthetic NAQD‑Env environment, the authors compare an original curriculum with an enriched one across multiple system‑prompt framings and evaluate four LoRA checkpoints of Qwen2.5‑3B‑Instruct against instruction‑tuned baselines. Results show that fine‑tuned checkpoints achieve higher decision agreement and withdrawal recall, reduce incorrect withdrawals, and narrow prohibited combinations, though they also omit valid event reports and exhibit mixed preservation of authorized actions.

By Mohamed Abouzahra
arXiv AI
Oct 31

When the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks

The paper introduces TRAILS, a taxonomy of 38 mechanisms that can compromise the reliability of large language model (LLM) read‑and‑evaluate tasks in evidence synthesis, such as study screening, data extraction, risk‑of‑bias assessment, and critical appraisal. It explains how these mechanisms can cause inconsistent or hidden failures across repeated LLM runs and outlines deployment settings, testing approaches, and mitigation strategies for each. The authors argue that repeatability or accuracy alone does not guarantee trustworthy judgments, emphasizing the need for human evaluation to verify that decisions are evidence‑based, free from external influence, and reproducible.

By Carole Lunny, Ian Goodman, Stefano Berrone, Connor TA Brenna, Emma K Reid, Ivan Perez-Neri, Shailesh Kolekar, Nityanand Jain, Ashwin Kamath, Lucas HCC Santos, Yulia Otmakhova, Heba Hussein, Diana M Cespedes, Gioia Dahdal, Salmaan Kanji
Hugging Face Trending Papers
Oct 29

When the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks

The paper presents TRAILS, a taxonomy of 38 mechanisms that can undermine the reliability of large language model (LLM) read‑and‑evaluate tasks in evidence synthesis, such as study screening and risk‑of‑bias assessment. It distinguishes failures that cause inconsistent judgments across repeated runs from those that systematically bias outcomes without obvious signs. The authors outline deployment settings, testing approaches, and mitigation strategies, and argue that repeatability or accuracy alone cannot guarantee trustworthy judgments, emphasizing the need for human evaluation of evidence grounding and process transparency.