arXiv Computation and Language
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Aug 28
Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI
The paper argues that large language models need adaptive reasoning rather than fixed reasoning budgets. It shows that over‑reasoning leads to high computational cost without accuracy gains, while under‑reasoning results in incorrect or incomplete solutions. The authors evaluate these failure modes on MATH‑500 and the GAIA benchmark, highlighting the need for dynamic reasoning allocation in agentic AI systems.
arXiv AI
Jun 12
The Illusion of Multi-Agent Advantage
arXiv:2606. 13003v1 Announce Type: new Abstract: Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed decision-making.
arXiv AI
Jun 9
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
arXiv AI
Oct 15
ReCreate: Reasoning and Creating Domain Agents Driven by Experience
arXiv:2601.11100v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are reshaping the industrial landscape. However, most practical agents still rely on human-designed scaffolds, ma...
arXiv AI
Jul 29
ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning
arXiv:2607. 25369v1 Announce Type: new Abstract: Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users.
arXiv AI
Oct 5
Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents
The paper introduces MIRA, a hierarchical architecture that separates meta-reasoning from execution for long-horizon research agents. An outer-loop meta-reasoner selects the next investigation based on a persistent research record, while an inner-loop executor carries out the chosen work order. The authors demonstrate that MIRA improves inference and compute allocation in theorem proving and neural-architecture research, and that a generative actor-critic variant (MIRA-AC) can be trained efficiently without directly optimizing long execution traces.