DecompRL is an RL method that learns modular code decomposition for LLMs, enabling exponential candidate generation via recombination to solve harder coding problems with lower GPU cost.
hub
Mapcoder: Multi-agent code generation for com- petitive problem solving.arXiv preprint arXiv:2405.11403
14 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
14
Pith papers citing it
1
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
ARIADNE combines blackboard architecture with MCTS to coordinate strategy, code, test, evaluation, and repair stages, yielding higher Pass@1 scores than prior LLM baselines on APPS, CodeContests, and related benchmarks.
BACE reformulates LLM code synthesis as Bayesian co-evolution of code and test populations anchored on minimal public examples, achieving superior performance on LiveCodeBench v6.
Debug2Fix integrates interactive debugging via subagents into coding agents, delivering >20% gains on GitBug-Java and SWE-Bench-Live while enabling weaker models to match stronger ones.
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
DryRUN lets LLMs create their own test inputs and run internal simulations for self-correcting code generation, matching the performance of test-dependent methods like CodeSIM on LiveCodeBench without public tests or external signals.
Multi-agent systems amplify minor stochastic biases into systemic polarization via echo-chamber effects in structured workflows, even with neutral agents.
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
A 520-run factorial experiment ranks an adversarial rewrite topology highest and cross-model review second among 12 LLM collaboration structures for software design, with parallel merge performing worst.
ATOM uses a nucleus-electron hierarchy and task-driven RL to generate budget-controllable multi-agent collaboration graphs for LLMs, claiming SOTA performance with up to 30% better token efficiency on six benchmarks.
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
SkillJect automatically generates poisoned agent skills — payload hidden in a helper script, inducement front-loaded in SKILL.md — achieving ~95% attack success across four LLM backends.
MARS introduces a four-agent MLLM system for risk-aware planning and personalized assistance in home robotics, claiming superior performance over state-of-the-art multimodal models on multiple datasets.
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.
citing papers explorer
-
DecompRL: Solving Harder Problems by Learning Modular Code Generation
DecompRL is an RL method that learns modular code decomposition for LLMs, enabling exponential candidate generation via recombination to solve harder coding problems with lower GPU cost.
-
ARIADNE: Agentic Reward-Informed Adaptive Decision Exploration via Blackboard-Driven MCTS for Competitive Program Generation
ARIADNE combines blackboard architecture with MCTS to coordinate strategy, code, test, evaluation, and repair stages, yielding higher Pass@1 scores than prior LLM baselines on APPS, CodeContests, and related benchmarks.
-
BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations
BACE reformulates LLM code synthesis as Bayesian co-evolution of code and test populations anchored on minimal public examples, achieving superior performance on LiveCodeBench v6.
-
Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?
Debug2Fix integrates interactive debugging via subagents into coding agents, delivering >20% gains on GitBug-Java and SWE-Bench-Live while enabling weaker models to match stronger ones.
-
No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
-
You Don't Need Public Tests to Generate Correct Code
DryRUN lets LLMs create their own test inputs and run internal simulations for self-correcting code generation, matching the performance of test-dependent methods like CodeSIM on LiveCodeBench without public tests or external signals.
-
Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
Multi-agent systems amplify minor stochastic biases into systemic polarization via echo-chamber effects in structured workflows, even with neutral agents.
-
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
-
LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Collaboration Topologies
A 520-run factorial experiment ranks an adversarial rewrite topology highest and cross-model review second among 12 LLM collaboration structures for software design, with parallel merge performing worst.
-
ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
ATOM uses a nucleus-electron hierarchy and task-driven RL to generate budget-controllable multi-agent collaboration graphs for LLMs, claiming SOTA performance with up to 30% better token efficiency on six benchmarks.
-
A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
-
SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
SkillJect automatically generates poisoned agent skills — payload hidden in a helper script, inducement front-loaded in SKILL.md — achieving ~95% attack success across four LLM backends.
-
MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence
MARS introduces a four-agent MLLM system for risk-aware planning and personalized assistance in home robotics, claiming superior performance over state-of-the-art multimodal models on multiple datasets.
-
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.