LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management

arXiv:2610.13075 · cs.AI · Submitted 2026-10-09 · Read on arXiv

cs.AI

Submitted: 2026-10-09

Updated: 2026-10-09

Code: https://github.com/anthropics/claude-code

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Agentic Reasoning — 1× in this paper · explained in 1 episode

Sources

• LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
• Coding Agents are Effective Long-Context Processors
• LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards
• Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
• LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger
• Evidence-State Rewards for Long-Context Reasoning
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• GLM-5: from Vibe Coding to Agentic Engineering
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation
• Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
• Kimi K3: Open Frontier Intelligence
• A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
• LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
• GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
• OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
• MemGPT: Towards LLMs as Operating Systems

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems