ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assi
Record details
Published: 5 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Agents & autonomy
Retrieved: 6 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
arXiv red teaming query · 5 August 2026
Characterizing Visual Accessibility Issues in AI Developer Tools: An Empirical Study
arXiv cs.HC · 5 August 2026
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
arXiv cs.AI · 5 August 2026
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
arXiv cs.AI · 5 August 2026
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
arXiv cs.AI · 5 August 2026
Failing Gracefully: Mitigating Impact of Inevitable Robot Failures
arXiv cs.HC · 5 August 2026
How to cite this record
ethics.ai (5 August 2026), “ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment,” evidence record 16917, https://ethics.ai/record/16917 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.