arXiv AI
Jun 16
PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
arXiv:2606. 16215v1 Announce Type: cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns.
Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train--deployment prompt mismatch.
Related stories
arXiv AI
Sep 3
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
UniToolCall introduces a unified framework for tool-use in large language model agents, standardizing toolset construction, dataset generation, and evaluation. The framework aggregates over 22,000 tools and creates a hybrid training corpus of more than 390,000 instances by combining ten public datasets with synthetically generated, structurally controlled trajectories. It models diverse interaction patterns—single‑hop vs. multi‑hop, single‑turn vs. multi‑turn, serial vs. parallel execution—and adds an Anchor Linkage mechanism to enforce cross‑turn dependencies, while converting seven public benchmarks into a common Query–Action–Observation–Answer format for fine‑grained evaluation.
arXiv Machine Learning
Jun 5
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
arXiv:2606. 05922v1 Announce Type: cross Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems.
arXiv AI
4d ago
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component o...
Hugging Face Trending Papers
Jun 4
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks.
arXiv AI
Jul 14
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
arXiv:2607. 10601v1 Announce Type: new Abstract: Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation.
arXiv AI
Jun 11
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
arXiv:2606. 05922v2 Announce Type: replace Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems.
arXiv AI
Jun 2
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
arXiv:2606. 00135v1 Announce Type: cross Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge.
arXiv AI
Aug 20
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
The paper introduces DART‑SD, a framework for improving multi‑turn tool‑calling agents by respecting the diamond‑shaped topology of task sub‑goals. It models the execution as an Interaction‑State Transition Graph, identifies critical topological breakpoints during rollouts, and uses these to retrieve recovery references. A progressive self‑distillation process then applies localized supervision only on recovery steps, preserving valid reasoning prefixes and enhancing policy diversity.
arXiv AI
Aug 3
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv AI
3d ago
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
Hugging Face Trending Papers
Aug 19
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
DART‑SD introduces a diamond‑topology aware framework for training large language models to perform multi‑turn tool‑calling. It models the execution process as an Interaction‑State Transition Graph, identifies critical topological breakpoints, and retrieves recovery references to guide localized self‑distillation. Experiments show that this approach outperforms traditional full‑trajectory baselines on complex multi‑turn tool‑calling benchmarks.