ACC: Compiling Agent Trajectories for Long-Context Training

• URL: http://arxiv.org/abs/2605.21850v1
• Date: Thu, 21 May 2026 00:47:03 GMT
• Title: ACC: Compiling Agent Trajectories for Long-Context Training
• Abstract summary: Agent Context Compilation converts trajectories from search, software engineering, and database querying agents into long-context QA pairs.<n>ACC is a simple but effective approach that can be combined with any existing long-context extension or training method.
• Score: 36.977301208747015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and receiving environment observations across many turns. The evidence needed to answer the original question is thus scattered throughout these turns, requiring integration of distant context segments. Nevertheless, standard agent SFT masks tool responses and only trains turn-level tool selection, creating a supervision blind spot where these scattered signals go unused. We propose Agent Context Compilation (ACC), which converts trajectories from search, software engineering, and database querying agents into long-context QA pairs that combine the original question with tool responses and environment observations gathered across multiple turns, training the model to answer directly without tool use. This makes the dependencies between the question and the evidence explicit, enabling direct supervision of long-context reasoning over distant segments without additional annotation. ACC is a simple but effective approach that can be combined with any existing long-context extension or training method, providing scalable supervised fine-tuning data. We validate ACC on long-range dependency modeling tasks through MRCR and GraphWalks, challenging benchmarks requiring cross-turn coreference resolution and graph traversal over extended contexts. Training Qwen3-30B-A3B with ACC achieves 68.3 on MRCR (+18.1) and 77.5 on GraphWalks (+7.6), results comparable to Qwen3-235B-A22B, while preserving general capabilities on GPQA, MMLU-Pro, AIME, and IFEval. Further mechanism analysis reveals that the ACC-trained model exhibits task-adaptive attention restructuring and expert specialization.

Related papers

• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering [26.55005240500685]
  ProMSA is a progressive multimodal search agent for Knowledge-based Visual Question Answering (KB-VQA)<n>Given an image-question pair, the agent iteratively chooses image search, text search, or stop, under explicit tool-call budgets and with deduplication to avoid redundant retrieval.<n>Experiments on E-VQA and InfoSeek show consistent gains over strong RAG and agent baselines, and improved retrieval and end-to-end accuracy.
  arXiv  Detail & Related papers  (2026-06-26T11:23:18Z)
• ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment [9.28566352356072]
  Andes is a framework that reimagines data generation as a plug-and-play emph agent skill.<n>We demonstrate that Andes improves automated alignment, securing state-of-the-art performance on PostTrainBench.
  arXiv  Detail & Related papers  (2026-05-31T15:03:50Z)
• Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR) [0.4635383898871528]
  We implement a multi-turn Code agent and post-train it with reinforcement learning using a custom harness and tools.<n>Our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model.
  arXiv  Detail & Related papers  (2026-05-13T21:27:21Z)
• Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context [64.09777482878083]
  We present a systematic study of long-context continued pre-training for LVLMs.<n>We first show that long-document VQA is substantially more effective than OCR transcription.<n>We introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget.
  arXiv  Detail & Related papers  (2026-05-13T17:52:53Z)
• UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents [22.52508596251479]
  We present UniToolCall, a unified framework for tool learning that standardizes the entire pipeline from construction and dataset generation to evaluation.<n>We convert 7 public benchmarks into a unified Query-Action--Observation-Answer (QAOA) representation with fine-grained evaluation at the function-call, turn, and conversation levels.<n>Under the Anchoror-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude.
  arXiv  Detail & Related papers  (2026-04-13T14:43:47Z)
• SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding [41.98672557723593]
  We introduce SWEQA-Pro, a benchmark constructed from diverse, long-tail repositories with executable environments.<n>We also propose a scalable synthetic data pipeline that powers a two-stage training recipe: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning from AI Feedback (RLAIF)<n> Empirically, a Qwen3-8B model trained with our recipe surpasses GPT-4o by 2.3 points on SWE-QA-Pro and substantially narrows the gap to state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-17T05:12:48Z)
• Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents [52.30603055218294]
  Trajectory2Task is a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios.<n>It converts valid tool-call trajectories into user-facing tasks with controlled intent adaptations.<n>We benchmark seven state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures.
  arXiv  Detail & Related papers  (2026-01-28T00:36:13Z)
• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction [0.18907108368038208]
  Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback.<n>This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction.<n>We show that a compact 3B- parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO), can learn effective policies for this task.
  arXiv  Detail & Related papers  (2025-11-14T08:44:58Z)
• Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search [70.63903518295785]
  We introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search.<n>Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks.
  arXiv  Detail & Related papers  (2025-10-30T09:10:36Z)
• SPELL: Self-Play Reinforcement Learning for evolving Long-Context Language Models [79.01078135582127]
  SPELL enables scalable, label-free optimization for long-context reasoning.<n>We introduce an automated curriculum that gradually increases document length and a reward function that adapts question difficulty to the model's evolving capabilities.
  arXiv  Detail & Related papers  (2025-09-28T13:08:10Z)
• Reading Between the Timelines: RAG for Answering Diachronic Questions [8.969698902720799]
  We propose a new framework that fundamentally redesigns the RAG pipeline to infuse temporal logic.<n>Our approach yields substantial gains in answer accuracy, surpassing standard RAG implementations by 13% to 27%.<n>This work provides a validated pathway toward RAG systems capable of performing the nuanced, evolutionary analysis required for complex, real-world questions.
  arXiv  Detail & Related papers  (2025-07-21T05:19:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.