AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.
hub
Self-collaboration code generation via chatgpt.ACM Trans
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
years
2026 12verdicts
UNVERDICTED 12representative citing papers
Chain-of-Thought prompting balances high accuracy with low energy use in small language models for code generation, while multi-sampling strategies add high energy costs for small accuracy gains.
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
Think-Anywhere lets LLMs invoke on-demand reasoning at any token during code generation via cold-start imitation followed by outcome-based RL, reaching state-of-the-art results on LeetCode, LiveCodeBench, HumanEval, and MBPP.
Adding active search tools to LLM context optimization works only when combined with a multi-candidate search-based training procedure that prunes contexts, delivering gains across low-resource translation, health, and reasoning benchmarks.
More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.
An AI-native TDD framework operationalizes classical TDD principles as prompt-level and workflow-level governance mechanisms in a layered multi-agent architecture to improve stability and reproducibility of LLM code generation.
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
The paper surveys the conceptual foundations, methodological innovations, challenges, and future directions of agentic reinforcement learning frameworks that embed cognitive capabilities like meta-reasoning and self-reflection into LLM-based agents.
citing papers explorer
-
AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.
-
Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation
Chain-of-Thought prompting balances high accuracy with low energy use in small language models for code generation, while multi-sampling strategies add high energy costs for small accuracy gains.
-
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
-
Think Anywhere in Code Generation
Think-Anywhere lets LLMs invoke on-demand reasoning at any token during code generation via cold-start imitation followed by outcome-based RL, reaching state-of-the-art results on LeetCode, LiveCodeBench, HumanEval, and MBPP.
-
Context Training with Active Information Seeking
Adding active search tools to LLM context optimization works only when combined with a multi-candidate search-based training procedure that prunes contexts, delivering gains across low-resource translation, health, and reasoning benchmarks.
-
AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
More capable LLMs and agents generate code with greater volume and architectural decay, following a Volume-Quality Inverse Law that neither functional correctness nor prompting mitigates.
-
QuantClaw: Precision Where It Matters for OpenClaw
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
-
Does Pass Rate Tell the Whole Story? Evaluating Design Constraint Compliance in LLM-based Issue Resolution
LLM agents resolve fewer than half of issues while satisfying design constraints despite passing tests, as shown by a benchmark of 495 issues and 1787 constraints from six repositories.
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
NAUTILUS is a prompt-driven harness that automates plug-and-play adapters, typed contracts, and validation for policies, benchmarks, and robots in learning research.
-
TDD Governance for Multi-Agent Code Generation via Prompt Engineering
An AI-native TDD framework operationalizes classical TDD principles as prompt-level and workflow-level governance mechanisms in a layered multi-agent architecture to improve stability and reproducibility of LLM code generation.
-
Agentic Insight Generation in VSM Simulations
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
-
A Brief Overview: Agentic Reinforcement Learning In Large Language Models
The paper surveys the conceptual foundations, methodological innovations, challenges, and future directions of agentic reinforcement learning frameworks that embed cognitive capabilities like meta-reasoning and self-reflection into LLM-based agents.