arXiv (All)
open access
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
Supervised fine-tuning (SFT) on offline agent trajectories is the standard approach for training specialized tool-using agents, but forcing models to imitate reasoning and actions token by token may harm other capabilities (e.g., general reasoning, tool calling, code generation) of the base model. I
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents#1132088
- Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling#1012307
- TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution#821362
- Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation#13078
- SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval#1077580
Record · ID 1155884
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive