Add paper: Harness Engineering for Language Agents (CAR framework)#79
Open
ChaoYue0307 wants to merge 1 commit into
Open
Add paper: Harness Engineering for Language Agents (CAR framework)#79ChaoYue0307 wants to merge 1 commit into
ChaoYue0307 wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds "Harness Engineering for Language Agents: The Harness Layer as Control, Agency, and Runtime" (Chaoyue He et al., Preprints 2026) to 1. Construction of LLM-based Agents → 1.3 Action → 1.3.1 Tool Using.
The paper formalizes the agent harness layer — the runtime/control loop wrapping tool execution and action — as Control, Agency, and Runtime (CAR), situates it in the arc from software → prompt → context engineering, audits 63 harness-relevant works, and proposes HarnessCard for reporting. Placed in Tool Using alongside the existing agent-platform/tool-learning surveys; happy to move it if a different section fits better.
Link: https://www.preprints.org/manuscript/202603.1756/v2 (DOI: 10.20944/preprints202603.1756)
Follows the list entry format and reverse-chronological ordering.