arXiv AI
Jun 16
ACC: Compiling Agent Trajectories for Long-Context Training
arXiv:2605. 21850v2 Announce Type: replace-cross Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs.
AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents
Related stories
arXiv AI
Jun 2
ACON: Optimizing Context Compression for Long-horizon LLM Agents
arXiv:2510. 00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observations.
arXiv Computation and Language
Oct 15
ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents
arXiv:2604.23069v2 Announce Type: replace Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may dro...
arXiv Computation and Language
Aug 31
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
ContextPilot is a proactive context‑management framework designed to improve long‑horizon agentic reasoning with large language models. It expands the toolset to include planning, long‑term memory, and soft context offloading, and introduces a reinforcement‑learning strategy that focuses on critical editing decisions and assigns action‑level advantages. Experiments on long‑context QA and deep search tasks demonstrate that ContextPilot achieves stronger performance with a more compact working context, outperforming existing baselines across various base models and benchmarks.
arXiv AI
5d ago
Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent
The paper introduces ExLabel, an LLM‑based, self‑evolving assistant that assesses task clarity and test coverage in SWE‑bench‑style software engineering datasets. ExLabel builds an experience bank from cross‑instance knowledge, enabling context‑aware judgments that outperform static rubrics. A new benchmark, SWE‑TQ, spanning eight programming languages, demonstrates ExLabel’s superior F1 scores and its ability to filter data that improves a coding model’s success rate on SWE‑bench Verified.
arXiv AI
Jul 23
PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
arXiv:2607. 20064v1 Announce Type: new Abstract: Long-horizon tasks require sustained perception, reasoning, and exploration, and are a persistent challenge for large language model (LLM) agents.
arXiv AI
Oct 1
Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives
The paper introduces Harness Primitives—reusable agent harness mechanisms mined from failed task trajectories—and a framework called STITCH that selects and composes these primitives into task‑specific harnesses at test time. This approach avoids generating or debugging harness code for each task, achieving up to 12‑point gains in task success over fixed harness baselines and outperforming human‑designed harnesses like Codex CLI. STITCH also demonstrates minimal test‑time overhead (2.7%) and scales efficiently with the size of the primitive library.
arXiv AI
Sep 18
An Empirical Study of Harness Design for Coding Agents
The study investigates how individual components of a coding harness—planning, action space, and context management—affect autonomous coding agents’ performance. By fixing the execution loop and varying these components across 176 settings on SWE‑Bench Verified and Terminal‑Bench 2.1, the authors find that context management is most valuable when context windows are tight, staging rule‑based elision before LLM summarization yields the best efficiency, planning serves as an accuracy scaffold for weaker models and a cost saver for stronger ones, and predefined tools help models with limited bash skills while bash‑capable models benefit from a bash‑only interface. Trajectory‑level analysis shows that context management lengthens execution paths, planning alters where trajectories terminate, and the action space determines code granularity, offering a modular framework for future harness design.
arXiv AI
21h ago
SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory
SUMONE is a lightweight summarizer designed to compress long interaction histories of language‑model agents. It is trained via masked reconstruction, where a frozen reconstructor predicts randomly masked parts of the original trajectory; reconstruction quality plus a length penalty yields a task‑agnostic reward for optimizing the summarizer with GRPO. At inference, only the summarizer remains, enabling plug‑and‑play context compression that reduces inference cost by roughly 78 % on DeepSearchQA and 75 % on SWE‑bench without affecting the underlying agent.
arXiv AI
Oct 12
SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories
SWE-Critix is a post‑training pipeline that creates generalist verifiers for coding‑agent trajectories. It uses supervised fine‑tuning followed by reinforcement learning to train 30B models on CodeForge‑Preview data, enabling the verifier to predict completion labels and generate natural‑language explanations. The approach raises classification accuracy from 57% to 78% on a held‑out test set.
arXiv AI
Jun 6
Enhancing Software Engineering Through Closed-Loop Memory Optimization
arXiv:2606. 05646v1 Announce Type: cross Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues.
arXiv AI
Aug 18
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
arXiv:2608. 15071v1 Announce Type: new Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.