This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

The paper demonstrates that using Reinforcement Learning from Verifiable Rewards (RLVR) significantly improves small language models' functional correctness in code generation, particularly when combi…

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…

The paper introduces OR-Space, a novel full-lifecycle workspace benchmark designed to rigorously evaluate industrial optimization agents by simulating real-world, multi-stage OR workflows that go beyo…

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…

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes a…

The paper introduces Atomic Decomposition and Recombination (ADR), a novel framework that generates genuinely novel and challenging verifiable code tasks, significantly improving the scalability of Re…

The paper proposes an objective-wise reputation-market mechanism to dynamically calibrate and gate LLM-generated expert priors in multi-objective Bayesian optimization, showing that dynamic calibratio…

KVerus is a retrieval-augmented system that significantly improves the scalability and resilience of formal verification for Rust code by managing complex cross-module dependencies and adapting to cod…

The paper proposes a hybrid reasoning framework where Large Language Models (LLMs) generate code to encode complex optimization problems into a preference-based Maximum Satisfiability (MaxSAT) format,…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to exi…

NANOZK introduces a novel, highly efficient zero-knowledge proof system that allows users to cryptographically verify that the output of a large language model (LLM) was generated by a specific, claim…

This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.

The paper proposes a federated formal verification architecture that treats verification as a polyglot proof system, successfully validating it on complex production subsystems like a Raft consensus m…

The paper proposes evaluating certified training methods by comparing their Pareto fronts across the natural-certified accuracy trade-off, revealing superior performance and previously unappreciated c…

This paper analyzes large-scale reasoning traces from LLM-based binary vulnerability analysis, identifying four structured, token-level implicit patterns that govern how LLMs explore code paths.

This paper benchmarks LLMs for smart contract security analysis, concluding that while LLMs show potential, their reliability is limited by lexical bias and requires integration with traditional stati…

The paper introduces Neuroforger, a system that combines a new formal specification language with LLMs and type checking to reliably generate and validate concrete violation witnesses (counterexamples…