Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations — Paper

Abstract

As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions. In comparison to the traditional machine learning systems, agentic workflows have complex failure modes with planning, tool invocation and dynamic environment interactions. In this paper, we investigate whether model's internal representations provide stronger signals of eventual task success in multi-turn agentic setups. We introduce two complementary methods: Latent Trajectory Dynamics (LTD), which summarizes changes in residual-stream representations across an an interaction trajectory, and the Action Representation Probe (ARP), which predicts success from representations formed at action decisions. Across three interactive benchmarks (Bash, SQL, Python) and three model families (Qwen14B, Qwen7B, DeepSeek6.7B), our methods consistently outperform surface level generation and sequence-based calibration baselines providing a zero-overhead reliability monitor that requires neither prompt alterations nor multi-sample rollouts.

Authors 3

Priyanka Mary Mammen, Emil Joswin, Srujananjali Medicherla

Specification

Official page: arxiv.org/abs/2609.09448
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
arXiv id: 2609.09448
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
Categories: cs.AI
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
PDF: arxiv.org/pdf/2609.09448
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
Primary category: cs.AI
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 8 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

8 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Priyanka Mary Mammen, Emil Joswin, Srujananjali Medicherla

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · arXiv id

1 claims · 1 propertiesShow all properties

arXiv idarxiv_id1

Claim history for arXiv id
Value	Valid from → to	Status	Source	Confidence	Extractor
2609.09448	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperDo Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
New paper: Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	1 h ago	2

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.