arXiv AI
Jul 2
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
arXiv:2607. 01223v1 Announce Type: new Abstract: When should an AI system's answer be trusted?
Evaluating and Guarding Citation Faithfulness in Agentic Scientific Synthesis
arXiv:2607. 20527v1 Announce Type: new Abstract: Agentic LLM systems such as OpenScholar and PaperQA2 read the scientific literature and return cited answers, and both they and their benchmarks already check whether those citations hold, with a fixed attribution model or human graders.
Related stories
arXiv AI
Jul 17
L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
arXiv:2509. 00761v4 Announce Type: replace Abstract: Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy.
arXiv AI
Jul 22
HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers
arXiv:2607. 18360v1 Announce Type: cross Abstract: Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set.
arXiv AI
Jul 2
Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences
arXiv:2607. 00738v1 Announce Type: cross Abstract: Large language models can generate polished scientific text that includes unsupported claims, allowing hallucinations to enter the archival record.
arXiv AI
Aug 12
Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
arXiv AI
Jun 17
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
arXiv:2510. 18003v2 Announce Type: replace-cross Abstract: The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research is evaluated by AI reviewers without human oversight.
arXiv AI
Jul 1
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
arXiv:2606. 31478v1 Announce Type: new Abstract: Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail.
arXiv Machine Learning
Jun 17
Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates
arXiv:2606. 17529v1 Announce Type: cross Abstract: Scientific machine-learning (SciML) surrogates approximate expensive simulations, but exact expected outputs for arbitrary inputs are unavailable (the oracle problem).
arXiv AI
Jul 15
Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs
arXiv:2607. 12650v1 Announce Type: cross Abstract: Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny.
arXiv AI
6d ago
TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs
arXiv:2608. 11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists.
Hugging Face Trending Papers
1d ago
Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees
Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing helpfulness or alignment, where no single reference answer exists.
arXiv AI
Aug 5
TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.