Papers9

#long-horizon reasoning

Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience

Zhongxiang Sun, Qipeng Wang et al.Jan 30arXiv

Deep search agents can plan and browse the web in many steps, but they often fail because they don’t notice when their own thinking drifts off-track.

#deep search agents#metacognition#consistency monitoring

Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Intermediate

Wenxuan Huang, Yu Zeng et al.Jan 29arXiv

The paper tackles a real problem: one-shot image or text searches often miss the right evidence (low hit-rate), especially in noisy, cluttered pictures.

#multimodal deep research#visual question answering#ReAct reasoning

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

Intermediate

Yaorui Shi, Shugui Liu et al.Jan 29arXiv

MemOCR is a new way for AI to remember long histories by turning important notes into a picture with big, bold parts for key facts and tiny parts for details.

#MemOCR#visual memory#adaptive information density

PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution

Intermediate

Minghao Yan, Bo Peng et al.Jan 15arXiv

PACEvolve is a new recipe that helps AI agents improve their ideas step by step over long periods without getting stuck.

#evolutionary search#LLM agents#context management

Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning

Intermediate

Yuyang Hu, Jiongnan Liu et al.Jan 8arXiv

This paper turns an AI agent’s memory from a flat list of notes into a logic map of events connected by cause-and-time links.

#event-centric memory#Event Graph#logic-aware retrieval

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

Intermediate

Junbo Li, Peng Zhou et al.Dec 18arXiv

Turn-PPO is a new way to train chatty AI agents that act over many steps, by judging each conversation turn as one whole action instead of judging every single token.

#Turn-PPO#multi-turn reinforcement learning#agentic LLMs

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Intermediate

Jingzhe Ding, Shengda Long et al.Dec 14arXiv

NL2Repo-Bench is a new benchmark that tests if coding agents can build a whole Python library from just one long natural-language document and an empty folder.

#NL2Repo-Bench#autonomous coding agents#long-horizon reasoning

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving

Intermediate

Songyang Gao, Yuzhe Gu et al.Dec 11arXiv

This paper builds a math problem–solving agent, Intern-S1-MO, that thinks in multiple rounds and remembers proven mini-results called lemmas so it can solve very long, Olympiad-level problems.

#long-horizon reasoning#lemma-based memory#multi-agent reasoning

Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning

Intermediate

Haiteng Zhao, Junhao Shen et al.Dec 11arXiv

This paper builds InternGeometry, a large language model agent that solves Olympiad-level geometry by talking to a math engine, remembering what worked, and trying smart new ideas.

#InternGeometry#geometry theorem proving#auxiliary constructions