Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reinforcement learning pipelines suffer from degraded instruction following, excessive rollout costs, and strict context limits. |
| Approach: | They propose a reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use where context length quickly becomes a bottleneck. |
| Outcome: | The proposed framework improves the success rate while maintaining the same or even lower working context length compared to baselines. |
Similar Papers
Context as a Tool: Context Management for Long-Horizon SWE-Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models rely on append-only context maintenance or passively triggered compression heuristics, leading to context explosion, semantic drift, and degraded reasoning in long-running interactions. |
| Approach: | They propose a new context management paradigm that elevates context maintenance to a callable tool . they propose 'cat' framework that injects context-management actions into complete interaction trajectories . |
| Outcome: | The proposed model outperforms ReAct-based agents and static compression baselines on SWE-Verified tests. |
LongReward: Improving Long-context Large Language Models with AI Feedback (2025.acl-long)
Copied to clipboard
Jiajie Zhang, Zhongni Hou, Xin Lv, Shulin Cao, Zhenyu Hou, Yilin Niu, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li
| Challenge: | In recent years, significant advancements have been achieved in the development of long-context large language models (LLMs). |
| Approach: | They propose a method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness. |
| Outcome: | The proposed method improves models’ long-context performance and enhances their ability to follow short instructions. |
Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing context window extension methods obstruct scaling external knowledge input. |
| Approach: | They develop a multi-agent framework to overcome two core bottlenecks in existing agent orchestration designs. |
| Outcome: | The proposed framework overcomes two core bottlenecks and improves inference-time knowledge integration without longer-context training. |
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schuetze, Volker Tresp, Yunpu Ma
| Challenge: | Large Language Models (LLMs) are stateless and limited by a finite context window, preventing them from maintaining knowledge across long conversations or evolving tasks. |
| Approach: | They propose a reinforcement learning framework that empowers LLMs to actively manage external memory through two specialized agents. |
| Outcome: | The proposed framework outperforms baselines and benchmarks across diverse question types, three benchmarks, and multiple model scales. |
PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents (2026.acl-long)
Copied to clipboard
Lei Wei, Xiao Peng, null Tt, Guannan Zhang, Chenhao Jiang, Hongyu Li, Lanbo Lin, Yuanwu Xu, Jiayao Liu, Kesu Wang, Bin Wang
| Challenge: | Large Language Model (LLM) agents struggle with ultra-long-horizon tasks requiring hundreds or thousands of interaction steps. |
| Approach: | They propose a framework that reconceptualizes context management as a Next Step Prediction problem. |
| Outcome: | The proposed framework improves task success rates and robust cross-lingual performance. |
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to managing working memory are based on external mechanisms that lack awareness of the agent’s reasoning state, leading to suboptimal decisions. |
| Approach: | They propose a framework that treats working memory management as learnable policy actions and enables joint optimization of information retention and task performance through end-to-end reinforcement learning. |
| Outcome: | The proposed framework matches models 16 larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities. |
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization (2026.acl-long)
Copied to clipboard
Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras
| Challenge: | Current reinforcement learning methods suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. |
| Approach: | They propose a novel RL algorithm for training large language models for multi-turn tool-integrated reasoning (TIR) that incorporates three innovations: turn-level reward assignment that provides fine-grained feedback for individual turns, return-based advantage estimation where normalized discounted returns are calculated as advantages, and self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. |
| Outcome: | The proposed algorithm outperforms GRPO by 3.0% across diverse math reasoning benchmarks and improves grepo by 3.9% on commonsense reasoning and program synthesis tasks. |
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models face quadratic computational costs, information forgetting, and context fragmentation . current methodologies diverge into three paradigms, each facing inherent trade-offs between Equal contribution. |
| Approach: | They propose a framework that enables efficient long-context inference via chunk-wise compression and selective memory recall. |
| Outcome: | The proposed framework reduces peak GPU memory usage and speeds up inference on multi-hop reasoning benchmarks. |
Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)
Copied to clipboard
Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently . |
| Approach: | They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model. |
| Outcome: | The proposed framework renders long texts into compact visual pages and processes them with a vision-language model. |
Cognitive Scaffold: From Fluid Context to Crystallized Memory for Long-Horizon DeepResearch Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Scaling LLM-based agents to long-horizon deep research is constrained by context-noise trade-off . solving a single query may require hundreds of interactions with noisy environments . |
| Approach: | They propose a factorized memory architecture that decouples the cognitive state into a Fluid Working Context for immediate reasoning and a persistent Knowledge Graph for long-term retention. |
| Outcome: | The Cognitive Scaffold outperforms baselines on Xbench-DeepSearch, BrowseComp-ZH, and GAIA . it achieves 74.7% Avg@3 and 87.0% Pass@3 on xbench, browseComp, and 88.3% Pass@3. |