# Reasoning for agents, planning and code Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/ ## Key facts - Reasoning for agents, planning and code: 2,143 papers on arXiv since 2022 (data through 7 Oct 2026). - 149 of its 2,143 mapped papers (7%) cite “OpenAI o1 System Card” (2024, arXiv 2412.16720). - 111 of its 2,143 mapped papers (5%) cite “LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code” (2024, arXiv 2403.07974). - 81 new papers 17 Sep–7 Oct. ## Most cited here - [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024), cited by 149 papers here - [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024), cited by 111 papers here - [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023), cited by 98 papers here - [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024), cited by 85 papers here - [SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities](https://mlsanity.com/paper/2502.12025/) (2025), cited by 75 papers here - [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022), cited by 71 papers here - [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023), cited by 66 papers here - [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024), cited by 66 papers here - [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023), cited by 61 papers here - [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023), cited by 53 papers here ## New (17 Sep–7 Oct) - [BRANCH: Bypassing Multi-Scanner AI Guardrails](https://mlsanity.com/paper/2610.10742/) (2026-10-07) - [From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery](https://mlsanity.com/paper/2610.09684/) (2026-10-07) - [System Switch: When Should a Fast Decision Model Stop and Think?](https://mlsanity.com/paper/2610.09683/) (2026-10-07) - [InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain](https://mlsanity.com/paper/2610.09671/) (2026-10-07) - [LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy](https://mlsanity.com/paper/2610.09466/) (2026-10-07) - [AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails](https://mlsanity.com/paper/2610.08923/) (2026-10-06) - [Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems](https://mlsanity.com/paper/2610.08901/) (2026-10-06) - [Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents](https://mlsanity.com/paper/2610.07948/) (2026-10-06) - [DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning](https://mlsanity.com/paper/2610.07835/) (2026-10-06) - [OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation](https://mlsanity.com/paper/2610.07787/) (2026-10-06) - [CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling](https://mlsanity.com/paper/2610.06829/) (2026-10-05) - [Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification](https://mlsanity.com/paper/2610.06790/) (2026-10-05) - [Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models](https://mlsanity.com/paper/2610.06439/) (2026-10-05) - [Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning](https://mlsanity.com/paper/2610.06366/) (2026-10-05) - [StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions](https://mlsanity.com/paper/2610.05241/) (2026-10-04) - [Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation](https://mlsanity.com/paper/2610.05219/) (2026-10-04) - [Monitorability Disposition in Large Reasoning Models](https://mlsanity.com/paper/2610.04914/) (2026-10-04) - [PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution](https://mlsanity.com/paper/2610.04737/) (2026-10-03) - [MLLMs Fail to Refuse when Using Tools Agentically](https://mlsanity.com/paper/2610.03938/) (2026-10-02) - [Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning](https://mlsanity.com/paper/2610.03102/) (2026-10-02) - [MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification](https://mlsanity.com/paper/2610.03056/) (2026-10-02) - [DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents](https://mlsanity.com/paper/2610.02351/) (2026-10-01) - [Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control](https://mlsanity.com/paper/2610.02038/) (2026-10-01) - [Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget](https://mlsanity.com/paper/2610.01236/) (2026-10-01) - [ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning](https://mlsanity.com/paper/2610.01184/) (2026-10-01) - [ABDA-NL: A Natural-Language Scenario Explorer for Argument-Based Reasoning](https://mlsanity.com/paper/2610.00947/) (2026-10-01) - [Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI](https://mlsanity.com/paper/2609.38143/) (2026-10-01) - [JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces](https://mlsanity.com/paper/2610.00437/) (2026-09-30) - [OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation](https://mlsanity.com/paper/2609.39727/) (2026-09-30) - [Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?](https://mlsanity.com/paper/2609.39578/) (2026-09-30)