Instruction Following

Follow this topic Ask about this topic

Momentum

11 papers in the last four weeks, down 8% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 85

Oct 5, 2026cs.AI

You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue

When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising failure: merely mentioning a rejected change can derail task execution, even when the user's final intent remains unchanged. To systematically study language model behavior under evolving user intent, we introduce Intent-Eval, a controlled benchmark spanning tool actions, code, databases, and mathematics. Across diverse tasks, models are vulnerable to both rejected proposals and superseded requirements, consistent with mentioned-as-in-effect confusion: conversational content is treated as active requirements even after it has been rejected or replaced. Accuracy degradation can deepen or persist as interaction continues, highlighting the need to distinguish what has been mentioned from what remains in effect. Building on this insight, we propose Intent-OPSD, a decision-conditioned on-policy self-distillation framework with Teacher and Student initialized from the same model. The frozen Teacher provides active-intent supervision from the complete task matching the user's decision, training the Student on the full dialogue to follow active requirements reflecting user intent.

Junle Chen, Wei Chen, Zhengjun Huang +5

HKUST · Tencent

Intent Classification Instruction Following Multi-Turn Dialogue Evaluation Language Model Robustness

Oct 4, 2026cs.CL

When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction Following

Verifiable instruction-following benchmarks often express each constraint through one fixed template. We test whether scores remain stable when the operational requirement is unchanged but its wording varies. We introduce WISE, a matched evaluation suite and reporting protocol instantiated on exact word count, keyword inclusion exactly once, and an inclusive 8--12 word range. Across 100 matched tasks, up to thirteen models from seven providers, and repeated generations scored over the complete visible output, wording alone produces substantial compliance shifts. In an avoidance-family panel, five avoidance and exclusion forms fall below the positive baseline, while constructional controls also shift compliance substantially: in the nine-model control panel, compliance is 54.9% for the original positive form, 48.2% for a longer positive form, 36.7% when the target appears later, and 33.8% for AVOID1. A strict JSON-structure probe shows wording sensitivity beyond counting, with a different direction of effect. Effect sizes, failure directions, weakest forms, and model rankings vary across realizations. Under the most disruptive exclusion form, the top-ranked model changes and 24.1% of strictly ordered model pairs reverse. Human validation further shows that unanimous agreement on an exact-count interpretation can coexist with substantially different model behavior. WISE supplements conventional scores with mean and worst-form compliance, wording gaps, failure profiles, and ranking stability.

Qishi Zhan, Seoyeon Jang, Zihan Dong +3

Marquette University · University of California, San Diego · Georgia Tech +3

LLM Evaluation Instruction Following Constraint Satisfaction Language Model Robustness Generative AI Evaluation

Oct 1, 2026cs.CL

Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles

As large language models (LLMs) move from standalone assistants into agentic workflows, evaluation must extend beyond scalar leaderboard accuracy to account for operational reliability, cost, latency, and token efficiency. We use an agentic ensemble of small language models (SLMs) with an SLM-judge-mediated feedback loop as a case study for such beyond-leaderboard evaluation. On the 541-prompt IFEval benchmark, the best ensemble achieves 97.34% strict prompt accuracy, exceeding the strongest standalone LLM baseline, gpt-5.4, by 5.81 percentage points while operating in a lower-cost regime. We then analyze the tokenomics and operational behavior behind this gain, including cost per sample, token composition, useful-output goodput, feedback-loop recovery, latency decomposition, and performance across instruction categories and constraint counts. Our results show that agentic SLM ensembles can trade additional test-time tokens and orchestration overhead for improved instruction-following fidelity, motivating multi-dimensional evaluation protocols for future agentic AI systems.

Alexei N. Skurikhin, Emily M. Taylor, Nathan A. DeBardeleben

Los Alamos National Laboratory Los Alamos, New Mexico, USA

LLM Inference Efficiency Language Model Generation Evaluation AI Agent Evaluation Small Language Models Instruction Following Language Model Ensembles

Sep 30, 2026cs.CL

Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness

Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between capability and alignment, and between capability and faithfulness, but a third tension remains underexplored: the alignment-faithfulness conflict. We show that aligned models systematically deviate from their inputs on unsafe or sensitive content without disclosing the modification, a failure mode we call alignment-induced unfaithfulness (AIU). Unlike capability-driven unfaithfulness, which comes from errors in knowledge or reasoning, this is induced by post-training mechanisms that override adherence to the input. We introduce FaithConflict, a controlled dataset isolating both conflicts, and two complementary taxonomies: behavioral (B1-B8) and chain-of-thought reasoning (C0-C6). Across models, AIU increases with scale and more sharply than capability-driven unfaithfulness, a reverse scaling law; intermediate checkpoints show it is amplified during post-training, with DPO the stage at which the gap both grows most and becomes least visible. Prompting-based mitigation does not resolve it, revealing a capability-alignment-faithfulness trilemma in the design and evaluation of LLMs.

Pardis Sadat Zahraei, Janvijay Singh, Gokhan Tur +1

University of Illinois Urbana-Champaign

LLM Alignment Instruction Following

Sep 30, 2026cs.AI

Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis

Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor sets for the same product, for example to preserve a particular motif. Recovering a recorded answer alone does not establish this ability to follow a preference. Satisfying such requests requires both coverage of relevant alternatives and control over which alternatives are favored. We introduce Route-Instruction Grounding and Steering (RIGS), a two-stage framework for instruction-conditioned retrosynthesis. Stage A trains a language projector, teaching it which alternatives an instruction favors or discourages. Stage B uses the projector learned in Stage A to steer a frozen generative model through lightweight residual adapters. We construct nested one-to-many training supports by pairing each product with increasing numbers of candidate precursor sets. Extensive experiments demonstrate that broader support helps the model generate a wider range of alternatives, and RIGS can learn to guide generation according to instructions. The relationship between coverage and control is consistent across model scales but non-monotone.

Xuemin Chen, Xiaozhuang Song, Xinjian Zhao +2

The Chinese University of Hong Kong, Shenzhen

Instruction Following Instruction Tuning

Sep 30, 2026cs.AI

A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?

Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs through naive prompting. Game development provides a demanding testbed, as long-form Game Design Documents (GDDs) describe requirements that must work together across game logic, visual rendering, and player interactions. However, existing game-development benchmarks typically use compact specifications and provide limited support for evaluating interdependent requirements across these aspects in long-form GDDs. We introduce A2Z GameSpec-Bench, a benchmark of 100 long-form GDDs for evaluating end-to-end game development by agents. We measure faithfulness by checking whether the game satisfies the GDD requirements and preserves the relationships among them. Each GDD is turned into a dependency-aware contract that contains rules, constraints, and prerequisite relations. Following game-development practices, we combine source-code inspection with agent-generated test policies for scenario-based replay and adaptive playtesting. The contract remains fixed across agents and revision rounds, while judgments and evidence linked to the same requirements support consistent comparison and failure detection. Our evaluations show that current agents struggle to jointly satisfy interdependent requirements across code implementation and actual play. Requirement-specific feedback improves GDD Fidelity by 10.9% relative to self-revision after two rounds. A2Z GameSpec-Bench assesses end-to-end specification-following ability beyond implementation judgments and provides targeted feedback to support more faithful game development. Code and datasets are available at https://a2z-gamespec-bench.github.io.

Seonho Lee, Wonryeol Jeong, Alberto Cereser +4

KRAFTON · KAIST · Korea National University of Arts

AI Coding Agents AI Agent Benchmarks Instruction Following Code Generation Evaluation

Sep 23, 2026cs.LG

Counterfactual Constraint-Conditioned On-Policy Distillation for Multi-Constraint Instruction Following

Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tuned models still routinely violate some of them. Existing approaches either augment supervision with sequence- or token-level RL rewards from external verifiers or learned graders, or use on-policy distillation (OPD) against a single full-context teacher whose probability mass becomes diluted as more constraints become simultaneously active. We propose CC-OPD (Counterfactual Constraint-Conditioned On-Policy Distillation), which inverts the standard supervision-generation direction in distillation. Rather than enriching the teacher with information beyond what the student sees, CC-OPD ablates each constraint from the teacher's conditioning in turn, and constructs the per-constraint signal from the resulting per-token probability differentials. The resulting per-token leave-one-out log-likelihood shifts are summed, clipped, and added to the vanilla OPD reward as a token-level shaping term. All shaping terms are obtained from the frozen teacher, without an external verifier during distillation, and the reward equals vanilla OPD wherever the aggregate shift is zero. Across two Qwen model pairs and seven benchmarks, CC-OPD achieves the highest average among all evaluated student-training methods. A 1.5B student trained with CC-OPD surpasses its own 7B RL-trained teacher on the MulDimIF benchmark.

Yanzhao Zheng, Yuanqiang Yu, Tianze Xu +6

Alibaba Group, Hangzhou, China

Reward Shaping Instruction Following Language Model Distillation On-Policy Distillation

Sep 12, 2026cs.AI

IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives

An external record may contain a procedure to apply or text to read, depending on the user's request. IBBench-Light tests both uses against the same record. Twelve semantic bases yield 144 matched pairs per model; four quantized instruction models produced 1,152 archived greedy responses. Paired exact-contract accuracy (PECA) requires both members to satisfy their output contracts. Qwen succeeds on 132 execute and 109 process prompts, but only 97 complete pairs, showing what marginal averages omit. We audit literal-target exposure and case normalization, then add 1,722 logged CPU generations to test directive-absent controls, twelve additional semantic bases, within-base wording changes, and generation stopping. In the pinned Phi rerun, changing the end-of-sequence (EOS) set changes exact paired success from 0/144 to 62/144. A bounded IHEval comparison uses the same SmolLM2 checkpoint and output budget while preserving its published instruction roles and scorer. The benchmark measures conditional task and output-contract success. Its task margins and paired count need to be read together with the stopping policy.

Kainan Zhou, Zhaoyi Li, Janet Sung +2

Google LLC Mountain View, CA, USA

LLM Evaluation Benchmark Design Instruction Following

Sep 10, 2026cs.AI

ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance

As LLM agents move from answering questions to carrying out procedures, failures can be unwarranted rather than visibly wrong: the final response looks acceptable even though the system skipped the check, branch, dependency, or invariant that made the answer justified. Output-only evaluation sees the answer, and trace-aware judging sees activity, but neither identifies which obligations were active for the query. We introduce CONTRACTEVAL, a diagnostic framework for making those active obligations explicit. It represents procedural instructions as query-active obligations and matches them against response or trace evidence, turning omissions, wrong branches, ordering errors, extra actions, invariant breaches, and output-contract violations into distinct conformance failures. On a controlled suite of audited procedural contracts, output-only and trace-aware LLM judges miss many injected structural failures; under gold expected and observed graphs, ContractEval detects and localizes all of them. LLM-backed extraction preserves much of this signal but remains calibration-sensitive. ContractEval is therefore not a compliance guarantee; it makes procedural conformance auditable rather than implicit in final-answer quality.

Praphul Singh, Shanu Kumar, Akshat Agarwal +1

Oracle Health AI · MBZUAI

LLM Agent Evaluation Instruction Following Language Model Auditing

Sep 7, 2026cs.CL

LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances

Robustness evaluation of large language models (LLMs) remains a critical challenge, particularly in assessing their sensitivity to perturbations in input data. In this work, we systematically evaluate LLM robustness across multiple dimensions, including word error rate, character repetition and duplication, modifications in choices, and variability in instruction following. To facilitate this evaluation, we construct a synthetic and augmented dataset encompassing a diverse set of LLM benchmarks, specifically targeting multiple-choice question (MCQ) datasets and instruction-following tasks. We conduct extensive experiments on LLMs of varying scales-small, medium, and large-as well as across base and instruction-tuned variants. Our analysis quantifies the variability in model responses under perturbed conditions and highlights discrepancies relative to baseline models. The findings provide insights into the stability of LLMs across different evaluation scenarios contributing to the development of more robust and reliable language models as well as robust evaluation methodologies.

Vamsi Krishna Kodavali, Rituraj Singh

Samsung

LLM Evaluation Instruction Following Language Model Robustness

Sep 7, 2026cs.CL

In-Place Instruction Following in Diffusion Language Models

Diffusion Large Language Models (dLLMs) generate text via bidirectional iterative denoising, naturally supporting user-specified constraints anchored at arbitrary output positions, a paradigm known as In-place Prompting (IPP). We formalize this as the In-place Instruction Following (IIF) task and construct IIF-Bench, a hierarchical benchmark spanning literal, style, and discourse-function constraints, paired with a rubric-based local-global evaluation protocol. An inference-time attention-bias probe suggests that vanilla dLLMs often under-prioritize constraint spans during denoising. We then propose GRAFT, an IPP-oriented post-training framework combining constraint-aware SFT and preference optimization. On four representative dLLMs, GRAFT raises the average IIF score from 57.75 to 73.10 (+15.35 points), with absolute gains of 15.91 and 15.57 points on literal and discourse-function constraints, while preserving general generation ability.

Zheng Nie, Zherui Li, Jiaming Zhang +3

National University of Singapore · Nanyang Technological University · Peking University

Instruction Following Diffusion Language Models Language Model Post-Training

Sep 7, 2026cs.AI

ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults

While autonomous mobile agents hold great potential for assisting older adults with smartphone usage, existing GUI benchmarks mainly rely on explicit, goal-oriented instructions and rarely capture the naturally occurring language patterns of older users, such as indirect speech, referential ambiguity, and under-specified requests. This mismatch between benchmark instructions and real-world elderly interactions may hinder reliable agent deployment. To address this gap, we present ElderBench, the first benchmark for evaluating mobile GUI agents in authentic elderly-oriented scenarios. ElderBench is constructed from 249 naturally elicited smartphone tasks collected from older adults across 20 applications. We first characterize the linguistic divergence between elderly instructions and existing GUI benchmark instructions from syntactic, semantic, and pragmatic perspectives. We then evaluate mainstream GUI agents and Vision-Language Models under both online and offline settings, revealing substantial performance degradation when handling elderly-oriented instructions. Through controlled instruction normalization, failure analysis, and fine-grained linguistic feature analysis, we further identify how elderly-specific language patterns contribute to agent failures. Our findings provide actionable design insights toward more adaptive, interpretable, and age-inclusive GUI agents for older adults.

Weide Zhan, Qumu Shaqu, Yuanqing Liu +6

Fudan University Shanghai, China

Mobile GUI Automation Computer-Use Agent Benchmarks GUI Agents Mobile GUI Agents Instruction Following

Sep 3, 2026cs.AI

Instruction Duplication as an Inference-Time Control Primitive

Procedural instruction following is a basic requirement for controllable language-model systems, especially when generated trajectories are inspected or repaired downstream. We introduce instruction duplication, a minimal black-box inference-time control that repeats only the procedural instruction, without retraining or decoding changes. Across seven instruction-tuned models, 300 medical multiple-choice questions, eight placement conditions, and 16,800 scheduled generations, moving from one to two copies raises the deterministic All-8 diagnostic--responses passing all eight observable tests--from 90.22% to 93.17% (+2.95 percentage points), eliminating 30.2% of the failures remaining after one copy. Pre-provisional TF-IDF recall rises from 73.44% to 74.81% (+1.38 points; Holm-adjusted p < .001), while final-answer accuracy remains exactly 60.21%. Premature commitment increases from 1.52% to 2.30% (p_Holm = .00536). A blinded challenge audit yields 10/30 directional confirmations, 20/30 perceptual ties, and no reversals; its prespecified 28/30 confirmation criterion is not met. Yet this distinction can matter operationally when a downstream system acts on the generated trajectory. In Answer Engineering (AE), where explicit trajectory state determines local repair, the published reason-first no-editing SSNHL endpoint was 25.1%; system-only AE was later reproduced at 84.2%, and the same trailing duplicate raised it to 97.1%. For conductive diagnostic branch preservation, the corresponding values are 58.9% published without editing, 78.6% with reproduced AE, and 73.8% with AE plus duplication--a within-AE decrease, but still 14.9 points above the no-editing baseline. Instruction duplication is therefore a low-complexity, placement-sensitive control whose practical value can emerge through the downstream system that consumes the exposed trajectory.

Victor Lavrenko

PeaceTech VC, Israel

Instruction Following Inference-Time Language Model Alignment

Sep 3, 2026cs.AI

DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents

Full-duplex voice agents must continuously decide when to speak, listen, backchannel, interrupt, overlap, and yield the conversational floor. Existing benchmarks evaluate these behaviors through explicit turn-management instructions, whereas voice agents are often configured through roles or personas from which appropriate conversational behavior must be inferred. We introduce DuplexSpeechBench-IFEval (DSB-IFEval), a benchmark for evaluating implicit instruction following in real-time spoken interaction. DSB-IFEval comprises 1,038 test cases derived from 240 controlled conversations spanning eight behaviorally contrastive assistant roles and five conditioning protocols: default behavior, explicit behavioral instructions, persona-implied behavior, combined persona-rule conditioning, and instruction conflict. We measure real-time floor management using the deterministic Instruction Adherence Score (IAS) and persona-consistent response content using the LLM-judged Persona Adherence Score (PAS). Across eleven real-time speech models, we find that executing an explicit floor-management policy does not reliably imply the ability to infer the same policy from a persona. Moreover, even frontier models such as GPT-Live-1 and Gemini-3.8-Live adapt their dialogue language to the assigned persona without consistently translating that persona into the appropriate full-duplex floor-management behavior. Finally, models that successfully resolve benign instruction conflicts often fail when safety-relevant role behavior should override an explicit directive. These results show that inferring role-implied behavior, executing it in real time, and resolving instruction conflicts remain distinct challenges for full-duplex voice agents.

Puneet Mathur, Dinesh Manocha

University of Maryland College Park, USA

AI Agent Benchmarks Instruction Following Multi-Turn Dialogue Evaluation Full-Duplex Spoken Dialogue Systems

Sep 2, 2026cs.CL

DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models

RAG has become the de facto method for incorporating new, corpus-specific knowledge into an instruction following LLM (Instruct LLM). Although RAG-based prompting improves factual grounding, it fails when retrieval is incorrect or incomplete, leading to hallucinations. Finetuning methods such as RAFT and PA-RAG enhance RAG by injecting new knowledge into the model's parameters, but require generating a massive amount of synthetic QA that covers the entire corpus. Extended Pre-Training (EPT) on the text corpus avoids the need for comprehensive synthetic data generation but compromises an Instruct LLM's instruction-following capabilities, necessitating instruction fine-tuning (IFT) after pre-training. However, IFT is costly and may be infeasible due to the unavailability of an instruction-tuning corpus. In this work, we propose DKL-Decoupled Knowledge Learning for Instruction-Tuned Language Models. Instead of doing EPT on the Instruct LLM, DKL performs EPT on its corresponding base LLM to infuse new knowledge. These knowledge infused weights are then merged with the Instruct LLM, imparting new knowledge without affecting their instruction-following capabilities. DKL is a lightweight method that avoids expensive instruction fine-tuning and relies on model merging to infuse the new knowledge into the Instruct LLM without destroying its instruction following capabilities. Empirical results show that DKL improves RAG accuracy from 54.17 to 79.26 on retrieval failure cases, while outperforming prior approaches with substantially less training data.

Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi +7

1IBM · 2Indian Institute of Technology, Madras

Knowledge Augmentation for Language Models Retrieval-Augmented Generation Continued Pretraining Instruction Following

Sep 2, 2026cs.AI

CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30 to 75 turns, and in 7 of 20 detectable defeats they failed to query within the 20 turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp

Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty +3

University of Oxford · Tony Blair Institute for Global Change · Google DeepMind +1

LLM Agent Evaluation LLM Tool Use Game-Playing Agents Long-Horizon Planning Instruction Following

Sep 1, 2026cs.CL

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quality gaps identified through production error analysis along three axes: instruction following, function-calling, and internal task distribution. Quality is tracked by offline benchmarks stratified to production traffic and scored by deterministic verifiers or calibrated LLM judges. Rather than optimising all objectives jointly, which introduces cross-domain reward interference, we train a separate GRPO expert per axis and merge them via two-stage SLERP. Each expert's reward exposes a distinct failure mode, namely semantic collapse, over-calling, and verbosity hacking, each requiring a domain-specific fix. In non-reasoning mode the recipe surpasses a

{\sim}7\times

larger by total parameters baseline on the in-house Arena with 69.6 to 65.8, instruction following with 0.85 to 0.83, and function-calling with 0.79 to 0.77, while lifting general dialogue benchmarks. The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.

Olga Tsymboi, Dmitrii Stoianov, Ramil Latypov +11

T-Tech

LLM Serving Instruction Following Model Merging LLM Post-Training Tool Use

Sep 1, 2026cs.CL

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output schema for a series of questions. On benchmarks that grade against every detail of the context, even strong open-weights models pass only 12-16% of tasks: a single overlooked rule fails the whole response. We argue this brittleness is structural: the dominant "read-and-reason" paradigm asks the model to extract, plan, generate, and self-verify in one forward pass. We therefore ask whether explicit context compilation can fix it, how it compares to existing long-context strategies (gist retrieval, multi-agent self-play), and where the resulting harness benefit holds across task structure and model scale. We propose the Context Compilation Architecture (CCA), whose central novelty is a typed intermediate representation (IR) with fixed slots (rules.{must_do, must_not, conditional}, output_spec, available_tools, data_profile) into which any prose context is compiled once; executable verifiers and a violation-gated correction loop follow as downstream consequences. On CL-bench (1,899 tasks across 4 open base models), CCA outperforms vanilla prompting and two long-context baselines (ReadAgent-P, Ctx2Skill) on every base model, lifting Kimi K2.5 from 15.4% to 21.4% with gains concentrated on rule-dense sub-categories. Code and cached completions are available at https://github.com/TonyQJH/cca-emnlp2026.

Jinhu Qi, Minda Hu, Wentao Zhang +4

The Chinese University of Hong Kong · Macao Polytechnic University · Xi’an Jiaotong University +1

Instruction Following In-Context Learning LLM Context Management

Aug 12, 2026cs.AI

Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia. No existing instrument measures this influence per clause, predicts it before delivery, or repairs it under matched budgets. \sysname{} closes the three gaps through the model API alone: a contract ledger pairs every constraint with an executable checker, records revocations as tombstones, and compiles the net constraint state ahead of time into a single specification; a sequential ablation probe measures per-clause adherence and incremental behavioral effect; a repair ladder operates under token- and attempt-matched budgets. On \dataname{} (\NTasks{} HumanEval tasks, \NClauses{} verified checkers), relapse at an 8B operating point climbs from \ScaleDelayedMTwo{} to \ScaleDelayedMEight{} as constraint load grows, while stronger models sit at floor. Under matched checkers, model, and budget, ahead-of-time compilation significantly reduces relapse against a no-ledger verifier-retry baseline (\RestoreDiff{}, 95% CI \RestoreDiffCI{},

p

\RestoreDiffP{}); adaptive ladder interventions stacked on top add no detectable gain (95% confidence excludes gains

\geq

\LadderExcludedGain{}). The probe predicts relapse before delivery (AUROC \AurocPrimary{}); a one-sentence tombstone note recovers about a third of the compilation effect and survives a placebo control. At \CostDeliveryFactor{} delivery overhead and \CostTotalHedged{} of API compute for every result, revocation failure becomes a measurable, predictable, and repairable property of dialogue state rather than an invisible one.

Haoyuan Zhu

Department of Electronic and Electrical Engineering University of Sheffield

Instruction Following LLM Reliability Multi-Turn Dialogue Evaluation LLM Context Management

Aug 12, 2026cs.AI

Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction

Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, output schemas. Individual constraints are handled proficiently, but the compositional regime, where many must hold jointly, remains poorly characterized: how rapidly does performance degrade, what governs the degradation, and can the collapse be mitigated? We introduce Constraint Saturation Evaluation (CSE), a procedurally generated benchmark that systematically varies the number of simultaneous constraints (k), with every constraint scored by a deterministic, rule-based verifier and zero LLM-judge involvement: 15 models, 36 constraint types, 369,753 checks at k=1-12. Three findings emerge. First, per-constraint pass rate decays gradually and predictably, while the chance of satisfying all k constraints collapses - a model passing individual constraints at ~41% at k=8 succeeds on all eight just 5.7% of the time. Second, constraints do not degrade equally: structural constraints lose 2x more baseline capability per added constraint than lexical ones, ordered by a comprehension-maintenance gap that separates constraints requiring sustained tracking from binary decisions immune to composition. Third, failures are nearly independent, which is what makes the accumulation multiplicative; the residual coupling that does exist tracks shared output features rather than pairwise interference - a wrong sentence count fails every constraint that reads it. Reliable instruction following breaks down beyond 5-6 simultaneous constraints: probe-level success falls below 50% at 7 constraints for the strongest model, and at 3 or fewer for 12 of 15.

Mariya I. Vasileva

Work done while at Meta Superintelligence Labs.

LLM Evaluation Instruction Following LLM Reliability Constraint Satisfaction

Aug 12, 2026cs.AI

Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents

When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads. To separate compliance from coincidence we introduce Against-Prior Accuracy (AP-Acc), which scores only rules labeled as opposing unprompted defaults, observed by re-running tasks with the rule withheld across nine probe builds and curated otherwise. Across 12 frontier models, accuracy spans 72.1-85.9% and AP-Acc 66.1-78.6%; every model is worse on against-prior rules, by 3.6 to 7.4 points (mean 5.81), and the direction survives a common-support analysis with item-clustered intervals. Aggregate scores therefore overstate compliance by a model-specific margin: prior control leaves the top build unchanged and exchanges three adjacent rank pairs. A counterbalanced conflict pilot on nine separate builds adds a second result: pooled precedence does not follow prompt depth, with system prompts, project files, and user instructions ahead of tool and skill descriptions.

Zining Huang, Haoran Que, Hong Zeng +8

ByteDance Seed · Tsinghua University · Peking University

AI Coding Agents LLM Agent Evaluation AI Agent Benchmarks Instruction Following

Aug 12, 2026cs.AI

EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval

Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealing a 57-point orchestration gap. Existing benchmarks assume clean retrieval with simple queries, failing to capture production conditions where noisy documents and multi-dimensional constraints coexist. We introduce EnterpriseRAG, a benchmark of 983 expert-validated samples across six domains that systematically simulates three failure modes absent from prior work: retrieval noise, knowledge gaps, and factual conflicts, coupled with complex instructions. Evaluation of 13 state-of-the-art LLMs reveals a severe instruction adherence collapse, where high per-constraint satisfaction masks low holistic compliance. Critical findings expose deep barriers under knowledge gaps and factual conflicts, even with reasoning-enhanced inference, indicating production RAG requires explicit context-aware protocols and calibrated judgment. EnterpriseRAG provides a reproducible foundation for measuring and closing these gaps, directly informing deployment decisions for enterprise-scale RAG systems. We will release the benchmark and evaluation framework upon publication.

Huiqi Miao, Xinbao Sun, Bo Wang +6

Jiutian Research, China Mobile, Beijing, China

Retrieval-Augmented Generation Instruction Following LLM Reliability RAG Evaluation RAG Robustness

Aug 11, 2026cs.AI

Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correctness regression costs O(2^|D|) in a prompt of |D| instructions. We name the resulting divergence catastrophic remembering, the inverse of catastrophic forgetting around which continual learning is organized. First, we characterize this phenomenon across 247,694 instruction lifetimes in 1,867 repositories: agentic prompts grow without bound, more than tripling over their lifetime (+226%), gaining +4.9 net instructions every commit; further, the older an instruction gets, the less likely it is to be deleted (log-hazard -0.032/commit). Then, we show that prompt comments can halt the growth: inverting IFEval yields verifiable worlds whose optimal prompts are known, and there comments encoding latent reasoning remove 99.3% of excess instructions (+211.3% to +1.4%). Finally, applying the same inversion to WildIFEval, we show that prompt comments can improve real-world agentic instruction-following by up to 23.1%. If English is the new code, why don't we have comments yet?

Kushal Chakrabarti

South Park Commons

LLM Prompting Agentic Code Generation Instruction Following

Aug 10, 2026cs.CL

UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following

Large language models (LLMs) are increasingly expected to follow long lists of constraints in complex instructions, and synthesizing instructions from a reference document (i.e., back-translation) is a widely used method to measure/enhance LLMs' ability to follow complex instructions. However, this method introduces a critical loophole: the constraint synthesis model copies text from the reference as a very specific constraint and the evaluated LLM trivially satisfies the constraint by copying its text in the response. To address these issues, we propose UNSPECIFIC, a novel framework that synthesizes constraints common to two similar reference articles to reduce copy-pasting, selectively hardens only trivially satisfied constraints to balance difficulty and naturalness, and evaluates satisfaction on both the generated article and its summary to penalize superficial instruction following. Consequently, we built the UNSPECIFIC benchmark on news, story, and blog domains to analyze the copy-pasting behavior of LLMs. Our results show that our synthesized constraints are not only more challenging (e.g., the satisfaction rate of GPT-5 Mini drops from 90% to 78%) and natural (LLM win-rate gap improves by 30%) from a human perspective but also mitigate the copy-pasting. We also find that a large portion of constraints are satisfied superficially (i.e., not satisfied in the core narrative of the article). The code and datasets are released at https://github.com/JeetDSharma/UNSPECIFIC.

Jeet Sharma, Balpreet Kaur, Jeremiah Hong +2

University of Massachusetts, Amherst, USA

Instruction Following Constraint Satisfaction Generative AI Evaluation

Aug 9, 2026cs.AI

LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs

The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequently used reference data, such as identifier lookup tables, directly in the server instructions: the system-prompt text a server hands to the host application. When a query concerns an entry of the embedded table, the model can act on it immediately instead of re-discovering the same information through a search tool. We test whether client LLMs actually consume such instruction-embedded data, reporting a 54,000-trial study across 24 LLMs (9 Claude, 6 Gemini, 9 GPT) on a production legal-information MCP server. A diagnostic condition that removes the competing search tool shows that failures are dominated by behavioral preference rather than missing capability. With search unavailable, 23 of 24 models read the embedded data reliably (hit ratio at least 98%); with a search tool merely present, 9 models drop below 15%. A 2^3 factorial analysis of three instruction-level interventions reveals strong interaction effects: combining all three restores at least 86% for 20 of 24 models, but individual interventions can backfire for specific model families. Per-server prompt engineering is therefore a workaround rather than a fix; we argue that MCP host applications should provide an explicit mechanism that places server instructions ahead of tool selection in the client LLM's deliberation.

Minhan Cho, Soyoung Park, Kihyeon Jeong +3

Remember & Company AI Lab · Sungkyunkwan University · National Assembly Research Service +2

LLM Inference Efficiency Instruction Following LLM Tool Use Model Context Protocol

Aug 8, 2026cs.AI

Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?

Structured output, where an LLM populates a predefined JSON schema, has become a default mechanism for data labeling and information extraction, but it also introduces a second instruction channel through schema descriptions. We tested whether classification-label definitions are better placed in the system prompt, user prompt, or schema description using a single-field classification task with nonce labels across ten model configurations from two vendors. Schema descriptions did not consistently outperform prompt-based placement; for GPT-4.1 and GPT-5.4 without reasoning, schema placement underperformed system prompts by 11-13 percentage points. Yet schemas are not inert metadata: when prompts and schemas conflicted, incorrect schema instructions caused accuracy drops of 5-45 points, with Claude Haiku 4.5 falling from 52.5% to 7%, indicating that schema instructions can override prompt instructions, and GPT-5.5 falling from 100% to 73%. Further, adding a required intermediate reasoning field before the label field improved schema-only accuracy by 15-24 points when headroom existed, exceeding system-prompt-only performance in every case tested. The effect held even for Claude Sonnet 4.6 at medium reasoning, where extended thinking alone did not produce a comparable gain. This suggests that schema design can affect how effectively models use information encoded in field descriptions. Overall, these results indicate that schema influence is model-dependent. In practice, the system prompt remains a safe default for definitions, but the bigger discipline is maintaining a single source of truth and preventing prompt/schema drift. More importantly, schema design itself may be a stronger lever than instruction placement. Practitioners should treat prompts and schemas as a unified instruction surface and empirically validate both placement and field design for their target model.

Sin-Ying Lin

Independent Researcher

Prompt Sensitivity Structured Prompting LLM Prompting Instruction Following Structured Output Generation

Jul 31, 2026cs.CL

Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction

When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instructions, Session Constraints (SCs), such as "do not delete any emails until I confirm," that are meant to constrain LLM's behavior for the remainder of a session but are silently dropped during compaction. To quantify this loss, we introduce COMPINT, an evaluation suite that evaluates compactors across three long-context scenarios: multi-turn chat, agentic trajectory, and long-horizon research. Current compactors retain only 17% of injected SCs on average, and most perform worse than running the same task without compaction. Retention varies sharply with compactor, prompt, context length, SC phrasing, and injection location, showing that the loss is systematic rather than tied to any single setting. We propose an SC-aware extractor that runs alongside the compactor as a plug-and-play module, achieving over 90% retention across all three scenarios without modifying the compactor or LLM. The COMPINT evaluation suite and accompanying implementation are available at https://github.com/ZhiqiEliWang/compaction-integrity.

Zhiqi Wang, Yichi Zhang, Dongwon Lee +1

The Pennsylvania State University

Persistent Memory for Language Models Instruction Following LLM Reliability LLM Context Management Context Compression

Jul 31, 2026cs.SE

Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation

Production prompts rarely carry a single instruction. One system message may require valid JSON, a word limit, three citations, and a fixed tone at the same time. We study how instruction-following degrades as such constraints accumulate. We introduce a benchmark that stacks 24 verifier-checked instructions, one to twenty at a time, and evaluate three production-tier LLMs (Claude Sonnet 4.6, GPT-5-mini, Gemini 2.5 Flash). Instruction-following degrades non-linearly: the follow rate falls from ~96% to as low as 20%, driven by a structured and reproducible set of pairwise conflicts. A single "output JSON" constraint, for example, is jointly unsatisfiable with nine others. We then evaluate a training-free remedy: an instruction compiler that rewrites the stacked prompt in a single LLM call and is reused across queries. Its benefit is capability-graded. It recovers up to +11 points of follow rate for weaker models, which are also the models most often deployed at scale, while leaving stronger models, which already internalise the same structure, essentially unchanged. Cluster-robust tests, same-baseline controls, and a within-family scaling ladder attribute the gain to the rewrite itself rather than to additional tokens, reordering, or measurement headroom. We release the benchmark, verifiers, and cached runs for full reproduction.

Atul Anand, Sourav Chattaraj

LLM Evaluation LLM Prompting Instruction Following

Jul 30, 2026cs.AI

IFHierBench: Hierarchical Instruction Following for Large Language Models

Instruction-following ability is critical for deploying large language models in real-world applications, where downstream components depend on the output satisfying specific constraints. Modern deployments increasingly handle the full task in a single LLM call, with one prompt specifying a layered output whose overall artifact, structural sections, and nested fields must each satisfy concrete constraints. Existing instruction-following benchmarks treat the constraint set as a flat list applied uniformly to the response, so they cannot scope a check to a particular section of the output. We introduce IFHierBench, a hierarchical instruction-following benchmark of 600 prompts stratified across four constraint-tree depths and 35 distinct constraints, each prompt paired with a deterministic checker that verifies satisfaction at every scope. Evaluating seven leading proprietary and open-weight models, we find that even the strongest model only marginally exceeds 50% prompt-level accuracy and that accuracy degrades sharply as constraint depth grows. Reliably following nested constraints remains a substantial gap for current LLMs, motivating future training methods that consider constraint adherence at finer granularity to achieve better instruction-following ability.

Yuetian Mao, Chunyang Chen

Technical University of Munich

LLM Evaluation Language Model Generation Evaluation Instruction Following

Jul 28, 2026cs.AI

HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following

Language-model agents are increasingly deployed under standing instructions: a system prompt, a policy file, or a skills document is placed in context, and the agent is trusted to let that document govern every action that follows. Existing benchmarks rarely test this deployment pattern directly; they measure whether an agent can complete a task, not whether a long, binding policy document constrains its behavior over an extended tool-use horizon. We present HANDBOOK_md, a benchmark of 65 agentic tasks modeled on how employees follow company handbooks. Each task places an agent in a self-contained company environment (a file workspace with mock email, chat, calendar, issue-tracking, and commerce services exposed over the Model Context Protocol) and instructs it to carry out routine professional work governed by an expert-written standard operating procedure of 20-124 pages. Tasks span five domains (finance, medical billing, insurance, logistics, and HR) and 10 fictional companies. To resist memorization, every task modifies one of 10 base handbooks, altering the specific rules and thresholds on which grading depends, so no two tasks share the same set of policies. Grading is fully deterministic: each task carries a rubric of programmatic criteria (824 in total) that check both that required actions occurred and that prohibited actions did not. Under strict grading, where a trial passes only if every criterion is satisfied, the strongest evaluated model passes 36.2% of trials, and most frontier models remain below 25%. Failures follow consistent patterns: agents let a plausible but unauthorized in-environment request override the standing policy, perform a required check and then act against its result, lose rule details over long horizons, and report compliance they did not achieve. We release the tasks, environments, and evaluation harness.

Liudas Panavas, Sebastian Minus, Bradley Monton +4

Surge AI*

Computer-Use Agent Benchmarks AI Agent Reliability Tool-Augmented Language Model Agents Long-Horizon Agent Evaluation AI Agent Benchmarks Instruction Following+1