Entity · paper

Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter

paperactiveexploring-extrinsic-and-intrinsic-properties-for-effective-reasoning-with-code-interpreter-c776e222·1 events·first seen Jun 16, 2026

Aliases: Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter

More like this (12)

Reasoning Enhancement Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection Code Interpreter Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)CharXiv Reasoning Multilingual Reasoning Cascades Need More Context Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning Reasoning Imitation Long-context Reasoning Benchmarks Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do AIMO Interpretability Challenge

Recent events (1)

5arXiv · cs.CL·Jun 16, 2026·source ↗

Systematic study of extrinsic and intrinsic properties for effective code interpreter reasoning in LLMs

Researchers investigate what behavioral properties make LLMs effective at reasoning with a Code Interpreter (CI), identifying two axes: extrinsic 'crucial tokens' and intrinsic 'cognitive behaviors' such as verification, backtracking, and backward chaining. Stronger CI reasoning models consistently exhibit higher prevalence of these properties. The paper shows that appending code-specific crucial tokens at inference time improves performance on mathematical, ordering, and optimization tasks, while augmenting training with cognitive behaviors improves SFT and RL performance in two of three evaluated models. The work also finds these behaviors reduce overthinking in incorrect responses and improve token efficiency.

Evaluation and Benchmarking Agent and Tool Ecosystem Exploring Extrinsic and Intrinsic Properties for Effective Reasoning with Code Interpreter