Pramana introduces a standardized, protocol-level wire format for autonomous agent outputs, ensuring that every consequential claim is accompanied by a verifiable artifact that can be re-executed by a…

The paper proposes a novel, efficient method for checking the factuality of claims generated by LLMs by framing it as a true/false reading comprehension task and incorporating explicit test-taking str…

AutoVerifier is an LLM-based agentic framework that automates the end-to-end verification of complex technical claims, enabling non-experts to generate evidence-backed intelligence assessments.

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

The paper introduces WIRE, a pipeline for diagnosing live intra-policy rule conflicts in LLM agents by identifying and testing specific rule pairs within a single prompt policy that can co-govern a re…

This survey provides a systematic framework and taxonomy for evidence tracing and execution provenance in LLM agents, addressing the difficulty of verifying and auditing complex agent behaviors.

This paper introduces Ghostwriter, an attack framework demonstrating that LLMs are highly vulnerable to adopting misleading viewpoints when provided with fabricated, yet credible-looking, evidence.

The paper introduces Contextual Belief Management (CBM) to address how LLMs should manage accumulating information over long interactions, showing that reinforcement learning significantly improves be…

This paper introduces a failure-aware observability framework to diagnose wasted computation in multi-agent LLM systems by mapping recurring failure modes to online trace signals.

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robu…

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated in…

The paper introduces CROP, a novel conformal procedure that provides rigorous statistical guarantees for certifying the longest safe prefix of a language model's reasoning trace, allowing for targeted…

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…

The paper introduces PSR extsuperscript{2}, a novel static analysis framework that significantly improves the detection of atomicity violations in smart contracts by combining structural path searchin…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

The paper introduces a diagnostic benchmark for selective Question Answering over conflicting, multi-source personal memory, demonstrating that specialized fusion resolvers outperform general LLMs, es…

The paper proposes a deterministic, version-aware aggregation method that significantly outperforms existing LLM-based systems for resolving memory conflicts in fact consolidation tasks.