Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?

arXiv:2609.39578 · cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.CL

Submitted: 2026-09-30

Updated: 2026-10-08

Terminology

• Robustness — 24× in this paper · explained in 5 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Verification — 13× in this paper · explained in 2 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Benchmarking — 9× in this paper · explained in 3 episodes
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Fidelity — 6× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 6× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Ablation — 3× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Economy of Minds — 2× in this paper
• Procedural Knowledge — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Agent Memory — 1× in this paper · explained in 1 episode
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• Paper Review — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
• Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• Towards Autonomous Mathematics Research
• GLM-5: from Vibe Coding to Agentic Engineering
• Automated Discovery Has No Universally Superior Harness
• DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
• LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
• Meta-Harness: End-to-End Optimization of Model Harnesses
• In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
• A lower bound for stepsize-based acceleration of gradient descent
• IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
• AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
• AutomationBench
• Harnesses for Inference-Time Alignment over Execution Trajectories
• Agent Workflow Memory
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering