Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Comments: 41 pages, 10 figures, 9 tables
Code: https://github.com/deepseek-ai/deepseek-harness
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
- OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks