Search papers, labs, and topics across Lattice.
AutoRestTest outperformed all competitors in the SBFT 2026 Tool Competition, revealing significant advancements in automated REST API testing.
VIGIL achieves over 95% recall in detecting policy violations in AI agent skills, significantly enhancing runtime enforcement capabilities.
Advanced RAG methods like GraphRAG and Agentic RAG can reduce token usage by up to 53%, but they don't always enhance generation quality as expected.
A robust multi-agent scaffold can unlock latent capabilities in fixed models, enabling a remarkable 67.4% issue resolution rate on SWE-bench Pro鈥攐utpacing the previous best by over 8 percentage points.
Exact-match retrieval metrics can mislead assessments of policy utility, as retrieved clauses perform nearly as well as gold-standard ones in decision-making tasks.
Bridging the intent-execution gap reveals that performance metrics alone can obscure significant behavioral differences among AI models in problem-solving contexts.
Direct token-level self-distillation can backfire, but Sibling-Guided Credit Distillation redefines credit assignment to enhance long-horizon tool-use without amplifying harmful behaviors.
Sustained self-improvement in LLM agents is achievable through a novel adaptive framework that outperforms traditional methods in dynamic task environments.
Open-source QUEST agents, trained solely on 8K synthetic tasks, rival or surpass proprietary research agents, proving that scaling data synthesis can unlock frontier performance.
LLMs can now automatically slim down and future-proof mathematical proofs, achieving 70% compression and 60% faster compilation by strategically rewriting them.
LLMs can now autonomously translate entire C projects to Rust with near-perfect accuracy, thanks to a novel agentic framework that dynamically navigates dependencies and iteratively verifies translations.
Domain-specific fine-tuning can induce "agentic collapse" in LLMs, but a surprisingly small amount of agentic data from *another* domain can bring those general tool-use skills roaring back.
Forget wrestling with language-specific tooling: ReCodeAgent autonomously translates and validates entire code repositories across diverse languages with a 60% boost in test pass rates.
LLMs can boost code performance by 25%, but only when working *with* compilers in a carefully orchestrated multi-agent system.
Memory-augmented LLMs get a strategic upgrade: MemMA uses multi-agent reasoning to proactively guide memory construction and repair, leading to significant performance gains.
Injecting knowledge graphs into LLMs boosts medical question generation by 8%, suggesting a simple way to patch up LLM knowledge gaps.
Open-source LLMs can now autonomously optimize AI accelerator kernels, matching the performance of proprietary models at a fraction of the cost.
