SkillFuzz is an execution-free fuzzing method that extracts skill contracts and applies contract-guided MCTS to discover over 1000 implicit intents in LLM skill marketplaces.
Swe-agent: Agent-computer interfaces enable automated soft- ware engineering
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
A harness for AI agents enabled construction of a Rust library with 100+ problem types and 200+ reduction rules for NP-hard problems in three months.
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
DUALVIEW is a dual-modal framework using Module Coupling, Function Call, Class Hierarchy, and Program Dependence graphs to enable persistent structural reasoning for agentic issue resolution, reporting gains on SWE-bench Pro and Verified.
LLVM-Bench supplies 423 validated LLVM issues and LLVM-Gym automates evaluation, showing LLMs are limited but an ensemble reaches 21.99% resolution.
citing papers explorer
-
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
SkillFuzz is an execution-free fuzzing method that extracts skill contracts and applies contract-guided MCTS to discover over 1000 implicit intents in LLM skill marketplaces.
-
Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
-
Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems
A harness for AI agents enabled construction of a Rust library with 100+ problem types and 200+ reduction rules for NP-hard problems in three months.
-
Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
-
Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution
DUALVIEW is a dual-modal framework using Module Coupling, Function Call, Class Hierarchy, and Program Dependence graphs to enable persistent structural reasoning for agentic issue resolution, reporting gains on SWE-bench Pro and Verified.
-
LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution
LLVM-Bench supplies 423 validated LLVM issues and LLVM-Gym automates evaluation, showing LLMs are limited but an ensemble reaches 21.99% resolution.