TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering

• URL: http://arxiv.org/abs/2605.05980v1
• Date: Thu, 07 May 2026 10:24:27 GMT
• Title: TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
• Abstract summary: We focus on two recurring failure modes where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence.<n>In this paper, we introduce TACT (Think-Act via activation Steering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure.<n>In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two *drift axes*, pointing from calibrated behavior toward each failure mode.
• Score: 70.99933391739154
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence. In this paper, we introduce TACT (Think-Act Calibration via activation Steering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure. In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two *drift axes*, pointing from calibrated behavior toward each failure mode (AUC $\approx$ 0.9). To mitigate agent drift, we project each step's activation onto these axes at test time and pull drifted ones back toward the calibrated region. Experiments show that TACT outperforms unsteered baselines across SWE-bench Verified, Terminal-Bench 2.0, and CLAW-Eval, lifting average resolve rate by $+5.8$ pp on Qwen3.5-27B and $+4.8$ pp on Gemma-4-26B-A4B-it while cutting steps-to-resolve by up to $26\%$. These gains frame agent drift as a steerable direction in the residual stream, and position TACT as a viable handle for reliable long-horizon agents.

Related papers

• How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method [4.37919186746582]
  We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent.<n>We extract phase-aware features by separating the reasoning and action spans, and calibrate them against a verifiable objective.<n>SU produces a failure-likelihood score that any downstream policy, such as routing, human intervention, or extra test-time compute, can consume directly.
  arXiv  Detail & Related papers  (2026-09-04T15:30:22Z)
• Can AI Agents Simulate A/B Test Outcomes? A Validation Framework for Agentic Experimentation [1.4180331276028662]
  A/B testing remains the standard for rolling out new features in the technology industry.<n>Can AI agents---conditioned on behavioral profiles and contextual descriptions of the intervention---simulate outcomes accurately enough to vet candidate treatments before committing live traffic?<n>We formalize this question as a emphSimulated Randomized Controlled Trial (S-RCT) and derive a two-layer error decomposition that separates agent approximation error from subsampling error.
  arXiv  Detail & Related papers  (2026-08-03T14:58:06Z)
• ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift [0.0]
  We propose ToolChain-CRC, a conformal risk-control method for retrieval-augmented and tool-using agents under drift.<n>The method treats each agent run as a full trajectory of actions, observations, and final output.<n>It builds step-level risk scores, combines them into a trajectory risk score, calibrates an accept-or-intervene rule, and adds an anytime alarm.
  arXiv  Detail & Related papers  (2026-06-16T20:27:37Z)
• Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning [13.759856460598087]
  Emergent misalignment (EM) occurs when a model behaves dangerously outside the finetuning task.<n>Standard training signals can miss this shift, making reliable detection costly if it depends on repeated behavioral evaluation.<n>We ask whether emergent misalignment can instead be detected from internal representations during finetuning.
  arXiv  Detail & Related papers  (2026-05-31T04:28:21Z)
• From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents [56.31499185764872]
  Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents.<n>We propose Patches-to-Trajectories (P2T), which uses $pstar$ as privileged information during curation and formulates trajectory construction as bi-objective optimization over per-step effectiveness and trajectory length.
  arXiv  Detail & Related papers  (2026-05-21T04:54:55Z)
• AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents [50.481033105867205]
  We introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories.<n>The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement.<n>It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity.
  arXiv  Detail & Related papers  (2026-03-15T16:13:58Z)
• TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning [4.928838343487574]
  Existing uncertainty proxies focus on single-shot text generation.<n>We introduce TRACER, a trajectory-level uncertainty metric for dual-control Tool-Agent-User interaction.
  arXiv  Detail & Related papers  (2026-02-11T22:23:56Z)
• ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration [68.89572566071575]
  ETAgent is a training framework for calibrating agent's tool-use behavior.<n>It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors.
  arXiv  Detail & Related papers  (2026-01-11T11:05:26Z)
• SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents [52.20768003832476]
  We analyze execution traces on $$-Bench (Airline/Retail) and SWE-Bench Verified.<n>We formalize emphdecisive deviations, earliest action, level divergences that flip success to failure.<n>We introduce cm, a model-agnostic, gradient-free, test-time safeguard.
  arXiv  Detail & Related papers  (2025-11-26T01:28:22Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers [44.344548601242444]
  We introduce a novel framework, Weakly-supervised RESidual Transformer (WeakREST), to achieve high anomaly detection accuracy.<n>We reformulate the pixel-wise anomaly localization task into a block-wise classification problem.<n>We develop a novel ResMixMatch algorithm, capable of handling the interplay between weak labels and residual-based representations.
  arXiv  Detail & Related papers  (2023-06-06T08:19:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.