τ -Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

Original title: $τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users.

By Singh, Saeidi, Hegde +2Oct 14, 2026

Score█████░░░░░4.6

VerdictWorth a reader's time today.

Read the original PDF Code

Abstract

In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Yet existing benchmarks largely assume cooperative and behaviorally stable users, leaving the effect of emotional variation on agent reliability underexplored. We introduce $τ$-Emotion-Bench, a ten-domain benchmark for evaluating tool-calling agents under controlled emotion-conditioned user interactions while preserving the underlying task objective. To scale both benchmark construction and agent training, we introduce Tracer, a scalable agentic data-generation pipeline that constructs grounded, policy-valid tasks and collects trajectories through an interactive agent--user--environment harness. By allowing dissatisfied users to terminate inefficient interactions, the harness provides an interaction-aware signal that filters trajectories with excessive user dependence and favors effective tool use. Experiments with two user simulators show that frontier agents remain unreliable, with substantial gaps between average task success and consistent task completion. Tracer-generated supervision consistently improves Qwen3 models across scales, generalizes to unseen domains, and transfers to $τ$-Bench and $τ$-Trait. Behavioral analyses further show that higher task success is associated with a better balance between tool execution and necessary user follow-up. Overall, $τ$-Emotion-Bench and Tracer provide a scalable framework for evaluating agent reliability under diverse user behaviors and improving tool-calling agents through interaction-aware supervision.

Rishitosh Kumar Singh, Amir Saeidi, Shamanthak Hegde, Shrinidhi Kumbhar, Chitta Baral

The editor's rubric

Heuristic review

Leverage4 / 5: A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).; 24% of this desk’s rubric
Magnitude2 / 5: Solid incremental gain on a meaningful problem.; 18% of this desk’s rubric
Evidence3 / 5: Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.; 14% of this desk’s rubric
Novelty3 / 5: A genuinely new approach to an open problem.; 16% of this desk’s rubric
Trajectory3 / 5: A clear path to scale.; 18% of this desk’s rubric
Stakes2 / 5: Benefits a professional community (practitioners, clinicians, engineers).; 10% of this desk’s rubric

Dimension	Level	Weight	What that level means
Leverage	████░ 4	24%	A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
Magnitude	██░░░ 2	18%	Solid incremental gain on a meaningful problem.
Evidence	███░░ 3	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	███░░ 3	16%	A genuinely new approach to an open problem.
Trajectory	███░░ 3	18%	A clear path to scale.
Stakes	██░░░ 2	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose, new method); breadth (generalizes); verification (held-out test); scale (scalable); stakes (general AI).

How the score was computed

rank-2026-10-18

Score█████░░░░░4.6

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Desks place stronger verdicts first, then use this score to order work within the same verdict.

Merit: 5.9 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 4.8 / 10; Shrunk toward the desk prior by editor confidence (42%).
Attention: 46%; Citations, upvotes, points, mentions.
Freshness: 30%; Half-life decay since publication.

Citations0 (reference 15, via semantic-scholar, Oct 18, 2026, 01:19 UTC)
Influential citations0 (reference 3, via semantic-scholar, Oct 18, 2026, 01:19 UTC)
Hugging Face upvotes17 (reference 25, via hf-daily, Oct 17, 2026, 13:49 UTC)
GitHub stars12 (reference 250, via hf-daily, Oct 17, 2026, 13:49 UTC)

The record

Reviewed by heuristic-v7 on Oct 18, 2026, 13:49 UTC. Paper type: method.
Categories: cs.AI, cs.CL
BRIEF, No.2 in the Artificial Intelligence edition of October 18, 2026.