TRACE: Capability-Targeted Agentic Training

• URL: http://arxiv.org/abs/2604.05336v1
• Date: Tue, 07 Apr 2026 02:22:44 GMT
• Title: TRACE: Capability-Targeted Agentic Training
• Abstract summary: We introduce TRACE, an end-to-end system for environment-specific agent self-improvement.<n>TRACE contrasts successful and failed trajectories to identify lacking capabilities.<n>It synthesizes a targeted training environment for each that rewards whether the capability was exercised.<n>It trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference.
• Score: 11.088296897059157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully solving a subset of tasks in the environment. Many existing approaches either rely on synthetic training data that is not targeted to the model's actual capability deficits in the target environment or train directly on the target environment, where the model needs to implicitly learn the capabilities across tasks. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify lacking capabilities, synthesizes a targeted training environment for each that rewards whether the capability was exercised, and trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference. Empirically, TRACE generalizes across different environments, improving over the base agent by +14.1 points on $τ^2$-bench (customer service) and +7 perfect scores on ToolSandbox (tool use), outperforming the strongest baseline by +7.4 points and +4 perfect scores, respectively. Given the same number of rollouts, TRACE scales more efficiently than baselines, outperforming GRPO and GEPA by +9.2 and +7.4 points on $τ^2$-bench.

Related papers

• GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis [42.18402261450695]
  GSAR (Goal-State-Anchor Reward) is a RL reward framework that supports scalable task generation and delivers reliable reward signals.<n>Our framework achieves over 90% accuracy on offline trajectory verification and performs closest to rule-based methods.
  arXiv  Detail & Related papers  (2026-08-24T06:27:47Z)
• Learning Generalizable Behaviors for Terminal Agents [72.62493560701414]
  We propose a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization.<n>Using this recipe, our RL-trained agent account the best performance among evaluated open-source RL-trained 8B models across four terminal-agent benchmarks.
  arXiv  Detail & Related papers  (2026-08-23T22:34:40Z)
• SPADE: Self-Play in Adaptive Synthetic Executable Environments [110.80471334001574]
  We introduce SPADE, a self-play RL framework in which a single LLM plays two roles.<n>The Environment Designer writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface.<n>We find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory.
  arXiv  Detail & Related papers  (2026-08-19T17:58:56Z)
• Terminal-World: Scaling Terminal-Agent Environments via Agent Skills [52.39713754337834]
  We introduce Terminal-World, a fully automated pipeline that uses agent skills as the central synthesis primitive.<n>We construct 5,723 training environments and train Terminal-World-8B/14B/32B, evaluated across 6 benchmarks.<n>Terminal-World-32B surpasses Nemotron-Terminal-32B on Terminal-Bench 2.0 by +4.5 Pass@1 (31.5) and achieves 43.8 Pass@3.
  arXiv  Detail & Related papers  (2026-05-20T08:14:51Z)
• EnterpriseBench Corecraft: Training Generalizable Agents on High-Fidelity RL Environments [0.10934862523101825]
  We show that training AI agents on high-fidelity reinforcement learning environments produces capabilities that generalize beyond the training distribution.<n>We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments.
  arXiv  Detail & Related papers  (2026-02-18T04:35:46Z)
• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning [62.499592503950026]
  Large language model (LLM) have empowered autonomous agents to perform complex tasks that require multi-turn interactions with tools and environments.<n>We propose Agent World Model (AWM), a fully synthetic environment generation pipeline.<n>We scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets.
  arXiv  Detail & Related papers  (2026-02-10T18:55:41Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation [65.3648667980258]
  Vision-language model (VLM) based GUI agents show promise for automating complex tasks, but face significant challenges in applying reinforcement learning (RL)<n>We propose DART, a Decoupled Agentic RL Training framework for GUI agents, which coordinates heterogeneous modules in a highly decoupled manner.<n>On the OSWorld benchmark, DART-GUI-7B achieves a 42.13% task success rate, a 14.61% absolute gain over the base model, and 7.34% higher than open-source SOTA.
  arXiv  Detail & Related papers  (2025-09-28T13:19:20Z)
• Generalizable End-to-End Tool-Use RL with Synthetic CodeGym [52.31172214690965]
  We introduce CodeGym, a framework that synthesizes diverse, verifiable, and controllable multi-turn tool-use environments for agent RL.<n>CodeGym rewrites static coding problems into interactive environments by extracting atomic functions or logic into callable tools.<n>Models of varying sizes and chain-of-thought configurations, trained in CodeGym, exhibit consistent out-of-distribution generalizability.
  arXiv  Detail & Related papers  (2025-09-22T03:03:56Z)

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.