Interactive dialogue games test a capability that static benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, and choose valid actions under changing constraints. We study this setting in the LM Playschool Challenge with a 2B open-weight model, and find that many failures are not only broad knowledge failures but also local decision failures: repeated guesses, malformed actions, and violations of feedback that the model has just seen. These diagnostics motivate a training recipe organized around three steps: acquire broad game participation through supervised fine-tuning, repair mechanically verifiable failures within one targeted dialogue-game family using turn-local preference pairs, and preserve general capabilities beyond these dialogue games. In the official final evaluation, our submission improves public clemscore from 10.67 to 38.92 and closed in-domain score from 13.41 to 41.17, while approximately preserving aggregate static performance (44.14 vs. 44.24 for the baseline). Out-of-domain clemscore remains low at 7.88, with the largest gains concentrated in unseen variants of the targeted family. Our results suggest that broad SFT brings most of the model's capability improvement; turn-local supervision can be effective when failure detection is precise, with observed transfer concentrated primarily within-family.
Figures & tables
Dialogue state
Model action
Local failure
After crane : red c/r/n ; yellow a ; green e
guess: crane
repeats guess
(same)
guess: abid
wrong length
(same)
guess: cable
uses red c
Table 1: Simplified Wordle failure states. The model output can be syntactically close to valid while violating a constraint entailed by the immediately preceding feedback. A real transcript exhibiting this pattern is reproduced in Table 7 .
Phase
Objective
LR / batch / len
Clem
—
Qwen3.5-2B
—
13.05
A. Acquire
broad SFT
2e-4 / 32 / 2048
43.85
B. Repair
turn-DPO: rpt + len
5e-6 / 16 / 1024
46.83
turn-DPO: inv + dup
5e-6 / 16 / 1024
45.52
C. Refine
branch-DPO
5e-6 / 16 / 1024
48.52
D. Preserve
delta scaling, s=0.85
no gradient
50.43 †
Table 2: Pipeline trajectory on the pinned public-development set (dataset 557d8caf , clembench ed39486 ). Batch denotes effective batch size; all Clem values are the full 14-game suite. Phases B and C train on Wordle data only. Both Phase B passes use β=0.1 ; Phase C uses β=0.2 . All trainable phases use LoRA on Qwen3.5-2B , AdamW, bf16, and one epoch; Phase C branches the model (factor 2, rounds 1–3, T=0.7 ) against a frozen reference. rpt/len = repeated guesses and bad length; inv/dup = invalid words and duplicated answer fields. † Mean of two runs (50.82 and 50.03). Per-game and per-phase Wordle detail: Tables 13 and 14 .
System
Base
Public
Stat
Closed ID
Closed OOD
Δ ID
Δ OOD
Baseline
Qwen3.5-2B
10.67
44.24
13.41
3.72
—
—
Qwen3.5-4B
26.66
51.33
34.02
17.99
—
—
Llama-3.1-8B
19.53
45.59
31.24
22.62
—
—
Qwen3.5-9B
31.91
53.90
41.12
24.91
—
—
Qwen3.5-27B
60.30
65.05
64.34
43.51
—
—
LLP llp-final
Qwen3.5-9B
53.39
57.80
59.23
22.09
+18.11
−2.82
Table 3: Official final evaluation results of the LM Playschool Challenge ( https://github.com/lm-playpen/lm-playschool-2026-final-results , snapshot 2dd5a533 ). Public is the public interactive clemscore; Stat is the static benchmark score; Closed ID and OOD are the organizer’s hidden in-domain and out-of-domain clemscores. Δ ID and Δ OOD are differences against each system’s own matching base. Submissions are sorted by public clemscore.
Played
Quality
Clem
(base → ours)
(base → ours)
(base → ours)
Public
27.22 → 78.63
39.20 → 49.50
10.67 → 38.92
Closed ID
47.32 → 82.62
28.33 → 49.83
13.41 → 41.17
Closed OOD
35.19 → 33.08
10.56 → 23.81
3.72 → 7.88
Table 4: Played and Quality decomposition of the official final evaluation. OOD Played falls below the untrained base, indicating that the OOD clemscore gain is driven entirely by higher conditional Quality on the episodes that remain in play.
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
Ph.
Data
Objective
LR / sched. / warmup
Batch / length / epochs
Other
A
9,522 rows
SFT, AdamW
2e-4 / cosine / 0.03
micro 8 × accum 4 = 32; 2,048; 1
LoRA r 16/ α 32/dropout 0.05/all-linear; bf16; grad. ckpt. on; seed 42
B1
1,905 pairs
DPO, β=0.1
5e-6 / cosine / 0.03
micro 1 × accum 16 = 16; 1,024; 1
bf16; grad. ckpt. off; separate frozen reference
B2
1,906 pairs
DPO, β=0.1
5e-6 / cosine / 0.03
micro 1 × accum 16 = 16; 1,024; 1
bf16; grad. ckpt. off; separate frozen reference
C
77 pairs
DPO, β=0.2
5e-6 / cosine / 0.03
micro 1 × accum 16 = 16; 1,024; 1
bf16; grad. ckpt. on; separate frozen reference; factor 2, rounds 1–3, T=0.7 , 256 new tokens
D
—
delta scaling s=0.85
no optimizer
—
multiply each lora_B by 0.85, then merge in fp32
Appendix
Table 5: Complete training configuration for the four effective phases. All trainable phases continue the same LoRA adapter on Qwen3.5-2B in bf16.
Game
Success
Capped
Train
AdventureGame
429
429
403
Codenames
2,402
700
669
DoND
1,256
700
663
GuessWhat
2,170
700
662
HotAirBalloon
1,102
700
658
ImageGame
1,018
700
662
Appendix
Table 6: Broad-SFT per-game counts at the reconstructed training-time snapshot ( cf23af92 ). Success counts successful episodes; Capped applies the 700-per-game limit; Train is the count after the 95/5 split.
The feedback shows that ‘r’ and ‘n’ are correct in their positions, while ‘c’, ‘a’, and ‘e’ are incorrect. … guess: ringer
GM
Error: The length of the guessed word is not 5. game_result = ABORT
Appendix
Table 7: A real Wordle failure from the broad-SFT checkpoint on the pinned public-development set (medium-frequency instance 14, target word grind ). The model reasons correctly about letter positions and then produces a six-letter guess. This is a diagnostic example, not a Phase B training row: Phase B pairs are built from clean successful episodes.
Row
Configuration
Clem
Stat
A
broad SFT only
44.09
39.88
B
A + turn-DPO pass 1
45.58
39.62
C
A + turn-DPO pass 1 (repeat)
45.94
40.96
D
C + turn-DPO pass 2
47.28
40.31
E
D + branch-DPO
45.21
41.54
Appendix
Table 8: Controlled single-host ablation. Rows B and C independently apply the same turn-DPO pass-1 configuration to the same effective parent; their difference ( +0.36 clem, +1.34 stat) estimates repeat-run variation. Adding branch-DPO to Row D reduces clem by 2.07 and raises stat by 1.23 (Row E). Row A’s adapter is byte-identical to the broad-SFT adapter that scored 43.85 on the pinned rail; the 0.24-point difference is evaluation variation measured in § A.4 . This controlled campaign and Table 2 use separate evaluation rails.
Arm
Pairs
Clem
vs. 50.43
Wordle-only solver
66
48.39
−2.0
All failures
675
44.15
−6.3
Wordle high-dose
66
44.99
−5.4
Conservative SVF
500
48.92
−1.5
SVF, then s=0.95
—
48.08
−2.4
SVF, then s=0.90
—
46.68
−3.8
Appendix
Table 9: Ten evaluated late-continuation endpoints. Eight are DPO runs ( β=0.20 , max length 1,024, micro-batch 1, separate frozen reference); two are training-free rescalings of a preceding DPO arm (marked —). SVF denotes success-versus-failure pairs. Of the eight DPO runs, five start from the selected s=0.85 adapter and three start from other parents (Phase A or unscaled Phase C). The 50.43 comparator is the mean of two evaluations of the selected adapter and serves as the contextual reference for this campaign.
Baseline
Ours
Benchmark
Played
Quality
Played
Quality
BBH
100.00
0.00
100.00
30.47
CLadder
100.00
48.51
100.00
46.53
EQ-Bench
97.06
64.78
94.12
56.43
IFEval
100.00
68.52
100.00
51.85
MMLU-Pro
100.00
40.71
100.00
38.05
Appendix
Table 10: Public static components of the official evaluation. Applying Eq. 1 gives statscore 44.24 for the baseline and 44.14 for our submission. The aggregate is approximately preserved, but the components are redistributed: BBH Quality rises by 30.47 while IFEval falls by 16.67 and EQ-Bench Quality by 8.35.
Qwen3.5-2B baseline
playornotplay (ours)
Game
Played
Quality
Eff.
Played
Quality
Eff.
Δ Eff.
TMW GraphReasoning
0.00
0.00
0.00
100.00
70.99
70.99
+70.99
ImageGame
80.00
12.03
9.62
97.50
71.46
69.67
+60.05
AdventureGame
0.00
0.00
0.00
100.00
58.33
58.33
+58.33
TextMapWorld
0.00
0.00
0.00
100.00
57.91
57.91
+57.91
TMW SpecificRoom
0.00
0.00
0.00
100.00
53.33
53.33
+53.33
Appendix
Table 11: Official hidden in-domain per-game decomposition, 21 scored configurations, sorted by change in effective score. Eff. is the displayed diagnostic Played×Quality/100 ; these values are not averaged to reconstruct the suite clemscore (Eq. 1 ).
Qwen3.5-2B baseline
playornotplay (ours)
Game
Played
Quality
Eff.
Played
Quality
Eff.
Δ Eff.
Wordle-crazy w/ Critic
6.67
0.00
0.00
36.67
90.91
33.34
+33.34
Wordle-crazy w/ Clue
6.67
50.00
3.33
36.67
100.00
36.67
+33.34
TA Frozen Lake
50.00
26.11
13.05
40.00
55.56
22.22
+9.17
TA Mastermind
0.00
0.00
0.00
15.00
33.33
5.00
+5.00
Wordle-crazy
3.33
0.00
0.00
80.00
4.17
3.34
+3.34
Appendix
Table 12: Official hidden out-of-domain per-game decomposition, 13 scored configurations from eight game families, sorted by change in effective score. The three Wordle-crazy configurations contribute 82.5% of total positive movement. Columns are as in Table 11 .
Game
n
Base
Broad SFT
Branch-DPO
Final
Δ Base → SFT
Δ SFT → Branch
Δ Branch → Final
AdventureGame
5
0.0
33.3
40.0
33.3
+33.3
+6.7
−6.7
Codenames
13
0.0
0.0
7.7
7.7
0.0
+7.7
0.0
GuessWhat
6
0.0
50.0
33.3
50.0
+50.0
−16.7
+16.7
ImageGame
4
35.8
81.2
89.8
85.2
+45.4
+8.6
−4.6
MatchIt ASCII
4
75.0
50.0
75.0
75.0
−25.0
+25.0
0.0
PrivateShared
4
0.0
35.1
21.3
18.3
+35.1
−13.8
−3.0
Appendix
Table 13: Matched per-game comparison of four checkpoints on the pinned public-development set (single host, single harness, dataset 557d8caf , clembench ed39486 ). The per-game score is the derived PgQg/100 ; it is displayed as 0 when Played =0 , although Quality itself is undefined there (Eq. 1 ). The overall clemscore is the product of macro-averaged Played and macro-averaged Quality over played games, not the mean of the per-game column, so per-game deltas do not sum to the overall delta. The Broad SFT column is the Phase A checkpoint and the Branch-DPO column is the Phase C checkpoint (Table 2 ). Δ Branch → Final includes gradient-free delta scaling and the fp32 merge, not additional training. Each game has 3–13 episodes; the changes are descriptive.
Checkpoint
Training scope
Suite Clem
W Played
W Quality
Rep./played ep.
Viol./ep.
Req. success
Broad SFT weights ∗
all games
43.85
66.7
0
3.00
0.33
88.9
Phase B pass 1
Wordle
46.83
0
—
—
1.00
63.9
Phase B pass 2
Wordle
45.52
66.7
0
0.00
0.33
91.7
Phase C
Wordle
48.52
100
0
0.00
0.00
100.0
+ scaling s=.85
none (no gradient)
50.82 / 50.03
0
—
—
1.00
69.4
Shipped fp32 merge
none (merge only)
48.70 / 49.10
0
—
—
1.00
69.4
Appendix
Table 14: Plain-Wordle behavior after each phase on the three public validation episodes (development evaluations; pinned dataset 557d8caf ). ∗ Three greedy evaluations of byte-identical weights span 43.35–44.09; the difference is evaluation noise (§ A.4 ). Suite Clem is the full 14-game clemscore; for the scaled and shipped artifacts we list the two runs of each. W Quality is undefined (—) when no episode is played. Rep./played ep. is the mean clembench Guess Repetitions over played episodes; Viol./ep. and Req. success are the mean Violated Request Count and Request Success Ratio (%) over all three episodes.
We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only successful game trajectories from Playpen, b) weighted turn-level SFT, and c) teacher-guided SFT. The teacher model (which is a larger model) is only used to fix formatting and evaluate examples, but does not create new gold actions. Our final model scores 57.12 clemscore and 42.68 statscore on the public Playpen validation. In the officially released challenge results, our model obtains the second-highest Playpen clemscore delta among submitted systems (which is approximately +36 over its base model). Our findings suggest that imitating full trajectories helps with playability, while turn-level and teacher-guided training usually improve decision-making and increase the overall score. Alternative procedurally heavy approaches like replay-repair and hard-example mining did not help, which suggests that small models are performant simply by using careful curation strategies rather than aggressive changes. We make available both the model and the code for reproducibility.
Syed Mahbubul Huq, Pranava Madhyastha
City, University of London · The Alan Turing Institute
Dialogue games represent a challenging setting where complex cognitive skills are required to accomplish tasks while coordinating with other players. Considering that language represents an interface for both understanding the game rules and executing actions, it is reasonable to assume that training on a specific language game will enhance specific capabilities that might be relevant for other tasks as well. Motivated by this rationale, in this paper, we investigate how knowledge transfers across different dialogue games. We study transferability by finetuning LLM models on games from the clembench suite (Chalamalasetti et al., 2023) and performing two analyses: i) we derive a task-transferability graph using a binary integer optimization program from Zamir et al. (2018), using task performance as the main metric; and ii) we compute task vectors (Ilharco et al., 2022) for each game to study similarities across finetuned models and their task transferability. In our first analysis, we find that some games benefit more from transfer than finetuning, and that the visuospatial family (e.g., exploration games) transfers best. With our task vector analysis instead, we find that similarity-based approaches capture game-role relationships but almost no transferability patterns, suggesting that more complex metrics are required.
Filippo Momentè, Mir Nafis Sharear Shopnil, Andrea de Varda +5
University of Trento · Technovative Solutions Ltd · Massachusetts Institute of Technology +2
Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns. Yet recent work shows that LLMs perform far worse in this multi-turn setting than in a single turn with same information being available at once, a phenomenon termed "Lost-in-Conversation." However, bridging this gap effectively remains an open problem. Here we introduce Found in Conversation (FiC), a training framework where a model teaches itself to find and recover its single-turn competence given underspecified multi-turn prompts. We develop View-Asymmetric Self-Distillation, which distills across two views of the same task information--single-turn view for the teacher, multi-turn view for the student--transferring strong single-turn behavior into weak multi-turn behavior. This requires no stronger external teacher, which is unavailable as even frontier LLMs exhibit this gap. Across model families (Llama, Qwen, Phi, and OLMo) and sizes (3B-14B), FiC recovers at least 92% of single-turn performance and reaches 100% on two Llama backbones, yielding more efficient and helpful multi-turn conversations with single-turn capabilities intact.