<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-etal-2026-niti">
    <titleInfo>
        <title>NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ayan</namePart>
        <namePart type="family">Banerjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shomrik</namePart>
        <namePart type="given">Barua</namePart>
        <namePart type="family">Banerjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sandeep</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Human decision-making in safety-critical domains is governed by abstract policies that intentionally omit exhaustive preconditions/ triggers and contingencies. Executing such underspecified policies reliably in open-world settings remains a fundamental challenge for large language models (LLMs). We introduce NITI, Neural Bridging for Incremental Execution and Trigger Inference from Underspecified Human Policies, a neuro-symbolic framework that treats LLMs not as autonomous planners, but as execution-time concretizers of human intent. NITI incrementally executes abstract policies via verifier-grounded interfaces, infers implicit applicability conditions, repairs execution through neural bridging when assumptions fail, and halts safely under state inconsistency. We evaluate NITI on two structurally distinct embodied domains: a new benchmark of World Cubing Championship 2×2 Rubik’s Cube scrambles (n=50) and a safety-critical automated insulin dosing task. Across multiple frontier LLMs, NITI enables reliable long-horizon execution without task-specific training or search with minimal contextualization infence overhead, substantially outperforming one-shot and chain-of-thought baselines. Our results show that compositional, verifier-grounded execution is essential for safe human–AI collaboration in open-world decision-making. Code and benchmark available here - https://github.com/ImpactLabASU/ACLNITI</abstract>
    <identifier type="citekey">banerjee-etal-2026-niti</identifier>
    <identifier type="doi">10.18653/v1/2026.findings-acl.2007</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.2007/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>40371</start>
            <end>40384</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies
%A Banerjee, Ayan
%A Banerjee, Shomrik Barua
%A Gupta, Sandeep
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F banerjee-etal-2026-niti
%X Human decision-making in safety-critical domains is governed by abstract policies that intentionally omit exhaustive preconditions/ triggers and contingencies. Executing such underspecified policies reliably in open-world settings remains a fundamental challenge for large language models (LLMs). We introduce NITI, Neural Bridging for Incremental Execution and Trigger Inference from Underspecified Human Policies, a neuro-symbolic framework that treats LLMs not as autonomous planners, but as execution-time concretizers of human intent. NITI incrementally executes abstract policies via verifier-grounded interfaces, infers implicit applicability conditions, repairs execution through neural bridging when assumptions fail, and halts safely under state inconsistency. We evaluate NITI on two structurally distinct embodied domains: a new benchmark of World Cubing Championship 2×2 Rubik’s Cube scrambles (n=50) and a safety-critical automated insulin dosing task. Across multiple frontier LLMs, NITI enables reliable long-horizon execution without task-specific training or search with minimal contextualization infence overhead, substantially outperforming one-shot and chain-of-thought baselines. Our results show that compositional, verifier-grounded execution is essential for safe human–AI collaboration in open-world decision-making. Code and benchmark available here - https://github.com/ImpactLabASU/ACLNITI
%R 10.18653/v1/2026.findings-acl.2007
%U https://aclanthology.org/2026.findings-acl.2007/
%U https://doi.org/10.18653/v1/2026.findings-acl.2007
%P 40371-40384

Markdown (Informal)

[NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies](https://aclanthology.org/2026.findings-acl.2007/) (Banerjee et al., Findings 2026)

• NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies (Banerjee et al., Findings 2026)

ACL

• Ayan Banerjee, Shomrik Barua Banerjee, and Sandeep Gupta. 2026. NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies. In Findings of the Association for Computational Linguistics: ACL 2026, pages 40371–40384, San Diego, California, United States. Association for Computational Linguistics.