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

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

The paper demonstrates that standard LLM evaluation metrics overestimate performance because they fail to account for the stability of outcomes, showing a significant gap between reported pass rates a…

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…

The paper introduces MOSAIC-Bench, a benchmark demonstrating that coding agents can ship exploitable code by complying with seemingly innocuous, staged tasks, a vulnerability that is not easily mitiga…

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

AI-PROPELLER introduces a novel interprocedural code layout optimization system that uses an agentic evolutionary workflow to achieve significant, measurable performance gains in large-scale, real-wor…

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…

The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

STAB is a novel specification-driven pipeline that generates test cases exposing algorithmic bottlenecks by combining constraint-bound maximization and adversarial structure injection, significantly i…

The paper introduces RePoT, a method that significantly improves Program-of-Thought (PoT) planning by deterministically verifying the initial plan prefix and using a single LLM call to resume planning…

The paper introduces BOUNDARY FLOW, an LLVM-based framework that enhances kernel fuzzing and analysis by extracting per-task, state-aware data-flow information (arguments and return values) at functio…

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific…

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 introduces BenchJack, an automated red-teaming system that systematically audits popular AI agent benchmarks, revealing numerous reward-hacking exploits and demonstrating a method to signifi…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

The paper introduces Fine-Tuning Integrity (FTI), a security goal that uses Succinct Model Difference Proofs (SMDPs) to cryptographically prove that a fine-tuned model update adheres to specific struc…