Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
arXiv cs.CL·Dean Light, Michael Theologitis, Kshitish Ghate, Shuyue Stella Li, Benjamin Newman, Chirag Shah, Aylin Caliskan, Pang Wei Koh, Dan Suciu, Yulia Tsvetkov
4d agoQuick Take
Deep Reasoning enables flexible, task-specific scaffolding in general-purpose agents through structured meta-reasoning.
Key Points
- Introduces Deep Reasoning for adaptive scaffolding.
- DOLORES outperforms state-of-the-art methods in multiple benchmarks.
- Reduces hallucinations and improves reasoning efficiency.
📖 Reader Mode
~2 min readAbstract:Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle when solving the task requires adapting the structure of reasoning itself. We introduce Deep Reasoning -- an inference-time approach for constructing task-specific scaffolds through structured meta-reasoning. Deep Reasoning uses a formal language that represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving, enabling decomposition principles to be encoded as in-context examples that guide test-time scaffold construction. We instantiate this approach in a general-purpose agent (DOLORES) that distributes complex tasks across more controlled reasoning threads. We evaluate it against state-of-the-art scaffolding methods across four hard benchmarks: multi-hop reasoning, long-chain question answering, long-context aggregation, and deep research-style information seeking. DOLORES outperforms all evaluated scaffolds across three model sizes and two model families, improving over the strongest evaluated scaffold baseline by 24.8% on average. DOLORES distributes cognition across structured, lower-load reasoning threads, thereby reducing premature termination and hallucinations. This advantage can even bridge the scaling gap, with an 8B version surpassing all evaluated 32B baselines from the same family in more than half the settings. These results point toward future agentic systems that treat scaffolding as adaptive reasoning, constructing the structure each task requires just-in-time.
| Comments: | Preprint under review |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.11388 [cs.CL] |
| (or arXiv:2605.11388v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11388 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dean Light [view email]
[v1]
Tue, 12 May 2026 01:21:37 UTC (2,968 KB)
— Originally published at arxiv.org
More from arXiv cs.CL
See more →arXiv cs.CL·Luis Lara, Aristides Milios, Zhi Hao Luo, Aditya Sharma, Ge Ya Luo, Christopher Beckham, Florian Golemo, Christopher Pal
2d ago FeaturedOriginal
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
AI Summary
A new LLM-based approach generates floor plans while adhering to numerical and topological constraints using reinforcement learning.