StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
- ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance
- SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
- ContextBench: A Benchmark for Context Retrieval in Coding Agents
- Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
- Context as a Tool: Context Management for Long-Horizon SWE-Agents
- GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
- CoAgent: Concurrency Control for Multi-Agent Systems
- SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
- LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
- Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
- Executable Code Actions Elicit Better LLM Agents
- The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- Learning Agent-Compatible Context Management for Long-Horizon Tasks
- CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding
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