EPS Dashboard

Authors: Dean Light, Michael Theologitis, Kshitish Ghate et al.

Summary

Current LLM agent scaffolds hard-code reasoning structures (plan, execute, verify, etc.) in advance, making them brittle when tasks require adapting the reasoning structure itself. The authors propose Deep Reasoning, an inference-time approach that constructs task-specific scaffolds via meta-reasoning: a formal language represents meta-reasoning as executable decompositions over associative inference, formal computation, and recursive subproblem solving. They instantiate this in DOLORES, a general-purpose agent that distributes complex tasks across controlled reasoning threads. DOLORES outperforms state-of-the-art scaffolds by 24.8% on average across multi-hop reasoning, long-chain QA, long-context aggregation, and deep research tasks, and an 8B version beats all evaluated 32B baselines from the same family in over half the benchmarks.

Main takeaways:

Hard-coded scaffolds are brittle when tasks require adapting reasoning structure, not just content
Deep Reasoning uses a formal meta-reasoning language to construct task-specific scaffolds at inference time
DOLORES distributes cognition across structured, lower-load reasoning threads (associative, formal, recursive)
Outperforms state-of-the-art scaffolds by 24.8% on average across four hard benchmarks
8B version surpasses all 32B baselines from same family in >50% of benchmarks—bridging the scaling gap via better structure

Relevance

Tangential—this is about flexible reasoning scaffolds for general agents, not persona behaviors or midtraining. The idea of distributing cognition across structured threads and meta-reasoning to adapt structure could loosely connect to how personas switch reasoning modes, but no direct link to my installation or activation steering work.

Threat model

Potential threat/caveat for clean result "Stretching turn count, completion length, or system-prompt length at train time fails to amplify marker uptake; the longest system prompt instead leaks across bystander personas (LOW confidence)": this item discusses benchmark.

Abstract

arXiv:2605.11388v1 Announce Type: new Abstract: 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.