arXiv AI By Yuan Sui, Yulin Chen, Yibo Li, Xue Jiang, Yufei He, Yihong Dong, Xiaoxin He, Tianyu Gao, Bryan Hooi

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

Read the original on arXiv AI →

The paper introduces TACT (Think-Act Calibration via activation Steering), a method to detect and mitigate agent drift—specifically overthinking and overacting—in language model agents performing complex software engineering tasks. By labeling trajectory steps and identifying two linear drift axes in the residual stream, TACT projects activations back toward calibrated behavior, achieving higher resolve rates and fewer steps-to-resolve on benchmarks such as SWE-bench Verified, Terminal-Bench 2.0, and CLAW-Eval.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 14

AgentAbstain: Do LLM Agents Know When Not to Act?

arXiv:2607. 10059v1 Announce Type: new Abstract: Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain.

By Xun Liu, Yi Evie Zhang, Vira Kasprova, Parisa Rabbani, Pardis Sadat Zahraei, Tianyu Zhang, Ali Ebrahimpour-Boroojeny, Varun Chandrasekaran
arXiv Machine Learning
Sep 17

Locating Hidden Failures Makes Long-Horizon Agents More Reliable

The paper introduces Traverse, a benchmark of 2,518 agent trajectories and 6,967 annotated mistakes across software engineering, computer use, and science tasks, revealing that failures often go unrecovered and can cause irreversible harm before a run is deemed successful. It shows that human judges struggle to detect the first mistake in most runs, while a 4‑billion‑parameter verifier called Scout can locate failures more effectively and improve task success when used to select among candidate runs. The study demonstrates that making failure detection inexpensive and reliable can enable long‑horizon agents to learn from their own mistakes and increase trustworthiness in autonomous AI.

By Salman Rahman, Yubin Kim, Mihir Parmar, A. Ali Heydari, Genglin Liu, Simon A. Lee, Weizhi Zhang, Arian Hosseini, Ahmed A. Metwally, Yuzhe Yang, Baharan Mirzasoleiman, Xin Liu, Pavel Izmailov, Saadia Gabriel, Mark Malhotra, Shwetak Patel, Daniel McDuff, Hamid Palangi
arXiv AI
Sep 2

Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling

The paper introduces an action‑class diagnostic framework for multi‑turn tool‑calling in large language model agents, breaking failures into action‑class miscalibration and action‑execution failure across a four‑class action space (TOOL_CALL, ASK, REFUSE, CONFIRM). It defines a self‑revealing upper bound (Acc GAR) to expose state‑grader masking of miscalibration and shows that miscalibration is a significant, previously hidden failure mode, especially for heavily tool‑trained families. The study demonstrates that calibration can be reshaped by context‑only perturbations, but the effects vary widely across models and perturbation mechanisms, underscoring the need for diagnostics beyond aggregate accuracy.

By Kangjia Zhao, Jiajun Li, Haozhan Shen, Wei Chow, Linfeng Li, Hang Song, Lingdong Kong, Chen Zhi, Tiancheng Zhao, Songhua Liu, Jianwei Yin